Duplicate from ibm-granite/granitelib-rag-r1.0

Co-authored-by: Fred Reiss <frreiss@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.gguf filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,6 @@
+**/.DS_Store
+
+# Ollama
+.venv
+_ollama/llama.cpp
+_ollama/models

README.md

@@ -0,0 +1,38 @@
+---
+license: apache-2.0
+language:
+- en
+base_model:
+- ibm-granite/granite-4.0-micro
+library_name: transformers
+---
+
+# Granite RAG Library
+
+The Granite RAG Library includes six adapters implemented as LoRA adapters for `ibm-granite/granite-4.0-micro`, 
+each of which expects as input a (single-turn or multi-turn) conversation between a user and an AI assistant, 
+and most of which also expect a set of grounding passages. 
+Each adapter has been developed for a specific task that is likely to be useful in Agentic RAG pipelines. 
+We give a brief overview of the functionality of each adapter, as the details can be found in each individual adapter's README.
+
+
+## Capabilities implemented as LoRA adapters
+
+The six adapters that have been implemented as LoRA adapters for `ibm-granite/granite-4.0-micro` and made available in this HF repository are:
+
+**Query Rewrite (QR):** Given a conversation ending with a user query, QR will decontextualize that last user query by rewriting it (whenever necessary) into an equivalent version that is standalone and can be understood by itself. While this adapter is general purpose for any multi-turn conversation, it is especially effective in RAG settings where its ability to rewrite a user query into a standalone version directly improves the retriever performance, which in turn improves the answer generation performance. This is a *pre-retrieval* adapter since its suggested use is before invoking retrieval. 
+
+**Query Clarification (QC):** Given a conversation ending with a user query, (and optionally relevant content such as RAG documents), QC will detect whether the last user query is underspecified (no clear interpretation or multiple valid interpretations) and, if so, formulate an appropriate clarification request back to the user.
+QR will decontextualize that last user query by rewriting it (whenever necessary) into an equivalent version that is standalone and can be understood by itself. The adapter is designed for conversational use cases where user queries may be ill-formed, unclear, or have multiple valid interpretations based on the underlying system or content.  This adapter is *pre-retrieval*OR  *pre-generation* since it can be used either before or after invoking retrieval
+
+**Context Relevance (CR):** Given a conversation ending with a user query, and an individual passage, CR classifies whether the passage is relevant, partially relevant, or irrelevant for answering the last user query - or if the passage may instead mislead or harm the downstream generator model’s response quality. This is a *pre-generation* adapter.
+
+**Answerability Determination (AD):** Given a conversation ending with a user query, and a set of passages, AD classifies whether that final user query is answerable or unanswerable based on the available information in the passages. It is valuable for restraining over-eager models by identifying unanswerable queries and preventing the generation of hallucinated responses. It can also be used to indicate that the system should re-query the retriever with alternate formulations, to fetch more relevant passages. This is a *pre-generation* adapter.
+
+**Hallucination Detection (HD):** Given a conversation ending with an assistant response, and a set of passages, HD outputs a hallucination risk range for each sentence in the last assistant response, with respect to the set of passages. This could be used in concert with sampling techniques that yield multiple generated responses, some of which could then be filtered according to their HD scores. This is a *post-generation* adapter since its expected use is after invoking the LLM to create the response. 
+
+**Citation Generation (CG):** Given a conversation ending with an assistant response, and a set of passages, CG generates citations for that last assistant response from the provided passages. Citations are generated for each sentence in the response (when available), where each citation consists of a set of sentences from the supporting passages. This is a *post-generation* adapter since its expected use is after invoking the LLM, and therefore can be used to create citations for responses generated by any model.
+
+## Recommended Use
+
+The recommended way to call all adaptors is through the [Mellea](https://mellea.ai) framework. For code snippets demonstrating how to use them please refer to the [Mellea intrinsics examples](https://github.com/generative-computing/mellea/tree/main/docs/examples/intrinsics).

_ollama/convert_io_yaml_files.py

@@ -0,0 +1,127 @@
+"""Convert vLLM io.yaml files into Ollama compatible io.yaml files.
+"""
+
+import argparse
+from pathlib import Path
+from typing import List
+import copy
+import json
+import yaml
+
+# No automated way, just add mappings here as needed.
+MAP_MODELS_HF_TO_OLLAMA = {
+    "granite-3.3-8b-instruct": "granite3.3:8b",
+    "granite-4.0-micro": "granite4:micro",
+}
+MAP_COLON = "_"
+LORA_TYPES = ["lora", "alora"]
+IO_FILE_NAME = "io.yaml"
+
+def find_all_model_paths(model_name: str) -> List[Path]:
+    """Find all paths with the given model name.
+    """
+    current = Path(".")
+    paths = []
+    for p in current.rglob(model_name):
+        rp = p.relative_to(current).parts
+        if p.is_dir() and not (rp[0].startswith(".") or rp[0].startswith("_")):
+            paths.append(p)
+    return sorted(paths)
+
+def map_model_path_hf_to_ollama(model_name: str, hf_path: Path) -> Path:
+    """Replace HF model name in the model path to Ollama model name.
+    """
+    ollama_path = Path(str(hf_path).replace(
+        model_name,
+        MAP_MODELS_HF_TO_OLLAMA[model_name].replace(":", MAP_COLON)
+    ))
+    return ollama_path
+
+def convert_io_yaml_hf_to_ollama(hf_path: Path, ollama_path: Path):
+    """Convert vLLM io.yaml files into Ollama compatible io.yaml files.
+    """
+    with hf_path.open("r") as f:
+        hf_yaml = yaml.safe_load(f)
+
+    # Move `response_format`
+    ollama_yaml = copy.deepcopy(hf_yaml)
+    if "parameters" not in ollama_yaml or not ollama_yaml["parameters"]:
+        ollama_yaml["parameters"] = {}
+
+    # Original field
+    response_format = json.loads(ollama_yaml["response_format"])
+
+    # Specific structure for Ollama's response_body
+    ollama_yaml["parameters"]["response_format"] = {}
+    ollama_yaml["parameters"]["response_format"]["type"] = "json_schema"
+    ollama_yaml["parameters"]["response_format"]["json_schema"] = {}
+    ollama_yaml["parameters"]["response_format"]["json_schema"]["schema"] = response_format
+    ollama_yaml["parameters"]["response_format"]["json_schema"]["strict"] = True
+
+    # Clear the original field
+    ollama_yaml["response_format"] = None
+
+    # Set movement of documents into message roles
+    ollama_yaml["docs_as_message"] = "roles"
+
+    # Change to max_tokens as max_completion_tokens is not yet supported:
+    # https://github.com/ollama/ollama/issues/7125
+    if "max_completion_tokens" in ollama_yaml["parameters"]:
+        ollama_yaml["parameters"]["max_tokens"] = ollama_yaml["parameters"]["max_completion_tokens"]
+        del ollama_yaml["parameters"]["max_completion_tokens"]
+
+    with ollama_path.open("w") as f:
+        yaml.dump(ollama_yaml, f, default_style=False, sort_keys=False)
+
+def convert_io_yaml_files(model_name: str, model_paths: List[Path]):
+    """Converts LoRA adapters into GGUF format.
+    """
+
+    for lora_type in LORA_TYPES:
+        for model_path in model_paths:
+            hf_lora_path = model_path / lora_type
+
+            ollama_lora_path = map_model_path_hf_to_ollama(
+                model_name,
+                hf_lora_path
+            )
+
+            # Convert "io.yaml" file
+            hf_io_file_path = hf_lora_path / IO_FILE_NAME
+            ollama_io_file_path = ollama_lora_path / IO_FILE_NAME
+            print(f"{IO_FILE_NAME} | {hf_io_file_path} -> {ollama_io_file_path}")
+
+            if not hf_io_file_path.is_file():
+                print(f"\t{lora_type} | HF {IO_FILE_NAME} does not exist")
+            else:
+                ollama_lora_path.mkdir(parents=True, exist_ok=True)
+                convert_io_yaml_hf_to_ollama(hf_io_file_path, ollama_io_file_path)
+
+def main():
+    """Main function.
+    """
+    parser = argparse.ArgumentParser(description="Convert IO YAML files for an Ollama backend")
+
+    parser.add_argument("--model", "-m", type=str, default="granite-4.0-micro",
+                        help="Name of model to convert (default: granite-4.0-micro)")
+    args = parser.parse_args()
+
+    model_name = args.model
+
+    if model_name not in MAP_MODELS_HF_TO_OLLAMA:
+        raise ValueError(
+            f"Model {model_name} not found in mapping list."
+        )
+
+    model_paths = find_all_model_paths(model_name)
+
+    print(f"Found {len(model_paths)} intrinsics for {model_name}:")
+    for model_path in model_paths:
+        print("\t", model_path.relative_to("."))
+    print("")
+
+    print("Converting LoRA adapters...")
+    convert_io_yaml_files(model_name, model_paths)
+
+if __name__ == "__main__":
+    main()

_ollama/convert_to_gguf.sh

@@ -0,0 +1,95 @@
+#!/bin/bash
+
+################################################################################
+# Shell script to convert all LoRA adapters in this repository into files
+# compatible with an Ollama backend.
+#
+# Tasks:
+# 1. Convert `.safetensors` files to `.gguf` files
+# 2. Create `Modelfile`s
+#
+################################################################################
+
+OLLAMA_DIR="_ollama"
+OLLAMA_MODEL_NAME=granite4:micro # Quantized model on Ollama
+OLLAMA_MODEL_DIR_NAME=${OLLAMA_MODEL_NAME/:/_}
+BASE_MODEL_NAME=granite-4.0-micro
+BASE_MODEL_ORG=ibm-granite
+OUTTYPE="q8_0"
+
+ENV_DIR=".venv"
+if [[ ! -d "$ENV_DIR" || ! -f "$ENV_DIR/bin/activate" ]]; then
+    echo "Creating virtual environment at: $ENV_DIR"
+    python3 -m venv "$ENV_DIR"
+else
+    echo "Reusing existing virtual environment: $ENV_DIR"
+fi
+source .venv/bin/activate
+which python
+python -m pip install --upgrade --quiet pip
+
+echo "Download base model"
+MODEL_DIR="$OLLAMA_DIR/models"
+mkdir -p $MODEL_DIR
+
+pip install huggingface_hub
+hf download $BASE_MODEL_ORG/$BASE_MODEL_NAME --local-dir $MODEL_DIR/$BASE_MODEL_NAME
+echo ""
+
+echo "Clone llama.cpp and install dependencies"
+LLAMA_CPP_DIR="$OLLAMA_DIR/llama.cpp"
+git clone --single-branch --branch master https://github.com/ggml-org/llama.cpp.git $LLAMA_CPP_DIR
+pip install -r $LLAMA_CPP_DIR/requirements/requirements-convert_hf_to_gguf.txt
+pip install -r $LLAMA_CPP_DIR/requirements/requirements-convert_hf_to_gguf_update.txt
+pip install -r $LLAMA_CPP_DIR/requirements/requirements-convert_lora_to_gguf.txt
+echo ""
+
+MODEL_GGUF_PATH="$MODEL_DIR/$BASE_MODEL_NAME/$BASE_MODEL_NAME-$OUTTYPE.gguf"
+if [[ ! -f $MODEL_GGUF_PATH ]]; then
+    echo "Converting model to GGUF: $MODEL_GGUF_PATH"
+    python $LLAMA_CPP_DIR/convert_hf_to_gguf.py $MODEL_DIR/$BASE_MODEL_NAME --outtype $OUTTYPE --outfile $MODEL_GGUF_PATH
+else
+  echo "Reusing existing GGUF model: $MODEL_GGUF_PATH"
+fi
+MODEL_GGUF_ABS_PATH=$(realpath $MODEL_GGUF_PATH)
+echo ""
+
+echo "Convert LoRA adapters to GGUF"
+LORA_DIRS=$( find . -name "lora" -path "*/$BASE_MODEL_NAME/*" -not -path "*.cache*" | sort | cut -c 3- )
+LORA_GGUF_NAME=Lora-$OUTTYPE
+for LORA_DIR in $LORA_DIRS; do
+    OUT_LORA_DIR=${LORA_DIR/$BASE_MODEL_NAME/$OLLAMA_MODEL_DIR_NAME}
+    mkdir -p $OUT_LORA_DIR
+    LORA_GGUF_PATH="$OUT_LORA_DIR/$LORA_GGUF_NAME.gguf"
+    LORA_GGUF_ABS_PATH=$(realpath $LORA_GGUF_PATH)
+    if [ ! -f "$LORA_GGUF_PATH" ]; then
+        echo "Converting LoRA to GGUF: $LORA_GGUF_PATH"
+        python $LLAMA_CPP_DIR/convert_lora_to_gguf.py $LORA_DIR --base $MODEL_DIR/$BASE_MODEL_NAME --outtype $OUTTYPE --outfile $LORA_GGUF_PATH
+    else
+        echo "Reusing existing LoRA GGUF: $LORA_GGUF_PATH"
+    fi
+
+    LORA_NAME=$(echo "$LORA_DIR" | cut -d "/" -f 1)
+    MODELFILE_PATH="$OUT_LORA_DIR/Modelfile"
+    echo "Creating $LORA_NAME | $MODELFILE_PATH"
+
+    # Use GGUF converted model
+    # printf "FROM $MODEL_GGUF_PATH\nADAPTER $LORA_GGUF_PATH\n" > $MODELFILE_PATH
+    # printf "FROM $MODEL_GGUF_PATH\nADAPTER $LORA_GGUF_PATH\n"
+
+    # Use quantized model from Ollama
+    printf "FROM $OLLAMA_MODEL_NAME\nADAPTER $LORA_GGUF_NAME.gguf\n" > $MODELFILE_PATH
+    printf "FROM $OLLAMA_MODEL_NAME\nADAPTER $LORA_GGUF_NAME.gguf\n\n"
+done
+echo ""
+
+echo "Clean up with these commands"
+deactivate
+# set -x
+echo "rm -rf $ENV_DIR"
+echo "rm -rf $MODEL_DIR"
+echo "rm -rf $LLAMA_CPP_DIR"
+echo "find . -name \"Lora-q8_0.gguf\" -delete"
+# set +x
+echo ""
+echo "Done."

answerability/README.md

@@ -0,0 +1,154 @@
+---
+license: apache-2.0
+language:
+- en
+pipeline_tag: text-generation
+library_name: peft
+library_name: transformers
+---
+
+# Answerability Classification
+
+## Model Summary
+
+**Anserability** is a RAG-specific adapter fine-tuned for binary answerability
+classification tasks. The model takes as input a multi-turn conversation and a
+set of documents, and classifies whether the user's final query is answerable or
+unanswerable based on the available information in the documents. We provide answerability capabilities implemented as LoRA adapters trained over Granite-4.0-micro and GPT-OSS 20b. This is the model card for the LoRA adapter trained over granite-4.0-micro. The model card for the LoRA adapter trained over gpt-oss-20b can be found [here](https://huggingface.co/ibm-granite/granitelib-rag-gpt-oss-r1.0/blob/main/answerability/README.md). 
+
+- **Developer:** IBM Research
+- **HF Collection:** [Granite Libraries](https://huggingface.co/collections/ibm-granite/granite-libraries)
+- **GitHub Repository:** https://github.com/ibm-granite
+- **Release Date:** March 18th, 2026
+- **Model type:** LoRA adapter for [ibm-granite/granite-4.0-micro](https://huggingface.co/ibm-granite/granite-4.0-micro)
+- **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)
+
+## Intended use
+This is a family of adapters that enables answerability classification for
+the final user query in a multi-turn conversation, with respect to a set of
+provided documents. The model is trained to determine whether the last user
+query is answerable or unanswerable, based solely on the information present in
+the documents. This makes it suitable for applications involving RAG and
+document-grounded chatbots, where knowing whether sufficient information exists
+to answer a query is crucial. The classification output from the answerability
+model can be used in several downstream applications, including but not limited
+to: 
+- Filter out unanswerable questions before sending them to generation in RAG
+setting. By classifying a query as unanswerable upfront, the system can prevent
+hallucinated or misleading responses. 
+- Re-query the retriever to get more
+relevant documents. If a query is initially deemed unanswerable, the retriever
+can be re-invoked with alternate formulations to fetch more relevant documents.
+
+**Adapter input**: The input to the answerability adapter is an
+OpenAI-compatible chat completion request, containing a list of conversation
+turns that can alternate between the `user` and `assistant` role and ending with
+a `user` turn, as well as list of documents.
+
+**Adapter output**: The output of the answerability adapter is the result of the
+original chat completion request formatted as a JSON object as follows:
+```json
+{
+  "answerability_likelihood": <float>
+}
+```
+
+### Example
+
+**Input conversation:**
+
+| Role | Message |
+|------|---------|
+| assistant | Hello there, how can I help you? |
+| user | What is the square root of 4? |
+
+**Input documents (answerable case):**
+- Document 1: "The square root of 4 is 2."
+
+**Output (answerable):**
+```json
+{
+  "answerability_likelihood": 0.9999646429576308
+}
+```
+
+**Input documents (unanswerable case):**
+- Document 1: "The square root of 8 is not 2."
+
+**Output (unanswerable):**
+```json
+{
+  "answerability_likelihood": 0.0001234567890123
+}
+```
+
+## Usage Examples
+
+The recommended way to call this adapter is through the [Mellea](https://mellea.ai) framework. For detailed examples on how to use this and other intrinsics, please refer to the [Mellea intrinsics examples](https://github.com/generative-computing/mellea/tree/main/docs/examples/intrinsics).
+
+
+## Evaluation: Answerability Classification
+
+We evaluated the model on binary answerability classification using MT-RAG
+Benchmark. In this setting, the model is given the full multi-turn conversation
+history along with the supporting documents. This benchmark evaluates the
+model's ability to assess answerability when the final user query can also
+depend on prior turns for context. The following table presents results
+comparing baselines and frontier models with task-specific answerability
+adapter on the answerability classification task on MT-RAG data. The LoRAs
+consistently outperform frontier models, converging near \~90% accuracy
+regardless of base model size. Even small models like Granite 4.0-micro, once
+fine-tuned, match or surpass much larger models, including GPT-4o.
+
+|                                      |    Models |     Unanswerable     F1    |     Answerable        F1    |     Classification        Accuracy    |     Weighted        F1    |
+|:--------------------------------------------:|:----------------------------------------------:|:--------------------------:|:---------------------------:|:-------------------------------------:|:-------------------------:|
+|                   Baselines                  |     BigBird (pre-trained embeddings) w/ MLP    |             73.4           |             65.2            |                  69.8                 |            69.6           |
+|                                              |       llama2-7b   as classifier (Full SFT)     |             88.2           |             85.9            |                  87.1                 |            87.1           |
+|     Frontier   Models      out-of-the-box    |                   GPT-OSS-20b                  |             77.3           |             58.3            |                  70.7                 |            68.5           |
+|                                              |                   GPT-OSS-120b                 |             70.2           |             68.9            |                  69.8                 |            69.6           |
+|                                              |                    GPT4o-mini                  |             82.7           |             78.1            |                  80.8                 |            80.6           |
+|                                              |                      GPT4o                     |             85.7           |             77.5            |                  82.5                 |            81.9           |
+|          Trained        LoRAs/aLoRAs         |              Granite   4.0-micro LoRA          |             90.9           |             90.0            |                  90.4                 |            90.5           |
+|                                              |                GPT-OSS-20b   LoRA              |             91.6           |             89.8            |                  90.8                 |            90.8           |
+|                                              |              Granite   4.0-micro aLoRA         |             90.0           |             89.4            |                  89.6                 |            89.7           |
+|                                              |               GPT-OSS-20b   aLoRA              |             90.4           |             88.6            |                  89.6                 |            89.6           |
+
+## Training Details
+
+### Training Data
+
+The training data uses the publicly available Government corpus from
+[MT-RAG](https://arxiv.org/pdf/2501.03468) as the source of documents. Based on
+this corpus, we constructed a dataset consisting of a mix of human-created and
+synthetically generated multi-turn conversations. It includes two types of
+examples: (1) Answerable queries, where the final user question can be answered
+based on the provided documents. These examples teach the adapter to recognize
+when sufficient information is present to support an answer. (2) Unanswerable
+queries, where the documents lack the necessary information to answer the final
+user query. We used Mixtral as an automatic judge to validate the answerability
+labels and filter out noisy samples.
+
+### Framework versions
+
+- PEFT 0.14.0
+
+### Adapter Details
+
+| Property | LoRA |
+|---|---|
+| **Base Model** | ibm-granite/granite-4.0-micro |
+| **PEFT Type** | LORA |
+| **Rank (r)** | 32 |
+| **Alpha** | 32 |
+| **Target Modules** | q_proj, k_proj, v_proj |
+
+**Infrastructure:** We trained the granite-4.0-micro LoRA adapter on IBM's Vela cluster using 8 A100 GPUs.
+
+**Ethical Considerations:** The answerability adapter is designed specifically 
+for Granite 4.0 Micro and was trained on its behavior. While it may be applied 
+to other LLMs, it has not been validated for them.
+
+**Resources**
+- ⭐️ Learn about the latest updates with Granite: https://www.ibm.com/granite
+- 📄 Get started with tutorials, best practices, and prompt engineering advice: https://www.ibm.com/granite/docs/
+- 💡 Learn about the latest Granite learning resources: https://ibm.biz/granite-learning-resources

answerability/granite-3.3-8b-instruct/alora/README.md

@@ -0,0 +1,202 @@
+---
+base_model: ibm-granite/granite-3.3-8b-instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

answerability/granite-3.3-8b-instruct/alora/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ibm-granite/granite-3.3-8b-instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

answerability/granite-3.3-8b-instruct/alora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0647946a9301e2df4b3d57e080895d9645f23b889a0b1658e74706885b0821a
+size 94404160

answerability/granite-3.3-8b-instruct/alora/io.yaml

@@ -0,0 +1,25 @@
+# Model name string, or null to use whatever is provided in the chat completion request.
+model: ~
+# JSON schema of the model's output
+response_format: |
+  {
+    "type": "string",
+    "enum": ["answerable", "unanswerable"]
+  }
+transformations:
+  # Convert categorical answer to continuous value by decoding logprobs
+  - type: likelihood
+    categories_to_values:
+      "answerable": 1.0
+      "unanswerable": 0.0
+    input_path: []
+  # Convert scalar value to a record for consistency with other intrinsics
+  - type: nest
+    input_path: []
+    field_name: "answerability_likelihood"
+instruction: ~
+parameters:
+  # "unanswerable" can be 6 tokens at high temperatures
+  max_completion_tokens: 6
+# No sentence boundary detection
+sentence_boundaries: ~

answerability/granite-3.3-8b-instruct/lora/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ibm-granite/granite-3.3-8b-instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

answerability/granite-3.3-8b-instruct/lora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:437300147993aa317a98cbba16ce800905f9f292fc0776d25d2d995f4c7f3f27
+size 94404160

answerability/granite-3.3-8b-instruct/lora/io.yaml

@@ -0,0 +1,25 @@
+# Model name string, or null to use whatever is provided in the chat completion request.
+model: ~
+# JSON schema of the model's output
+response_format: |
+  {
+    "type": "string",
+    "enum": ["answerable", "unanswerable"]
+  }
+transformations:
+  # Convert categorical answer to continuous value by decoding logprobs
+  - type: likelihood
+    categories_to_values:
+      "answerable": 1.0
+      "unanswerable": 0.0
+    input_path: []
+  # Convert scalar value to a record for consistency with other intrinsics
+  - type: nest
+    input_path: []
+    field_name: "answerability_likelihood"
+instruction: ~
+parameters:
+  # "unanswerable" can be 6 tokens at high temperatures
+  max_completion_tokens: 6
+# No sentence boundary detection
+sentence_boundaries: ~

answerability/granite-4.0-micro/alora/README.md

@@ -0,0 +1,209 @@
+---
+base_model: ibm-granite/granite-4.0-micro
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:ibm-granite/granite-4.0-micro
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.2.dev0

answerability/granite-4.0-micro/alora/adapter_config.json

@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": [
+    100264,
+    78191,
+    100265
+  ],
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "ibm-granite/granite-4.0-micro",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.17.2.dev0@UNKNOWN",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

answerability/granite-4.0-micro/alora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62daf58a9e8d3ae147d4900fb863d55e94f825ff6bf05bb0d6da63ec15767ee3
+size 57703888

answerability/granite-4.0-micro/alora/chat_template.jinja

@@ -0,0 +1,118 @@
+{%- set tools_system_message_prefix = 'You are a helpful assistant with access to the following tools. You may call one or more tools to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>'  %}
+{%- set tools_system_message_suffix = '\n</tools>\n\nFor each tool call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.' %}
+{%- set documents_system_message_prefix = 'You are a helpful assistant with access to the following documents. You may use one or more documents to assist with the user query.\n\nYou are given a list of documents within <documents></documents> XML tags:\n<documents>' %}
+{%- set documents_system_message_suffix = '\n</documents>\n\nWrite the response to the user\'s input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.' %}
+{%- set g4_default_system_message = 'You are a helpful assistant. Please ensure responses are professional, accurate, and safe.' %}
+{%- if available_tools is defined and available_tools %}
+    {%- set tools = available_tools %}
+{%- endif %}
+{%- set ns = namespace(tools_system_message=tools_system_message_prefix,
+                       documents_system_message=documents_system_message_prefix,
+                       default_system_message=g4_default_system_message,
+                       system_message=''
+                       ) %}
+{%- if tools %}
+    {%- for tool in tools %}
+        {%- set ns.tools_system_message = ns.tools_system_message + '\n' + (tool | tojson) %}
+    {%- endfor %}
+    {%- set ns.tools_system_message = ns.tools_system_message + tools_system_message_suffix %}
+{%- else %}
+    {%- set ns.tools_system_message = '' %}
+{%- endif %}
+{%- if documents %}
+    {%- for document in documents %}
+        {%- set ns.documents_system_message = ns.documents_system_message + '\n' + (document | tojson) %}
+    {%- endfor %}
+    {%- set ns.documents_system_message = ns.documents_system_message + documents_system_message_suffix %}
+{%- else %}
+    {%- set ns.documents_system_message = '' %}
+{%- endif %}
+{%- if messages[0].role == 'system' %}
+    {%- if messages[0].content is string %}
+        {%- set ns.system_message = messages[0].content %}
+    {%- elif messages[0].content is iterable %}
+        {%- for entry in messages[0].content %}
+            {%- if entry.type== 'text' %}
+                {%- if ns.system_message != '' %}
+                    {%- set ns.system_message = ns.system_message + '\n' %}
+                {%- endif %}
+                {%- set ns.system_message = ns.system_message + entry.text %}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+    {%- if tools and documents %}
+        {%- set ns.system_message = ns.system_message + '\n\n' +  ns.tools_system_message + '\n\n' + ns.documents_system_message %}
+    {%- elif tools %}
+        {%- set ns.system_message = ns.system_message + '\n\n' + ns.tools_system_message %}
+    {%- elif documents %}
+        {%- set ns.system_message = ns.system_message + '\n\n' + ns.documents_system_message %}
+    {%- endif %}
+{%- else %}
+    {%- if tools and documents %}
+        {%- set ns.system_message = ns.tools_system_message + '\n\n' + ns.documents_system_message  %}
+    {%- elif tools %}
+        {%- set ns.system_message = ns.tools_system_message %}
+    {%- elif documents %}
+        {%- set ns.system_message = ns.documents_system_message %}
+    {%- endif %}
+{%- endif %}
+{%- if ns.system_message %}
+    {{- '<|start_of_role|>system<|end_of_role|>' + ns.system_message + '<|end_of_text|>\n' }}
+{%- else %}
+    {{- '<|start_of_role|>system<|end_of_role|>' + ns.default_system_message + '<|end_of_text|>\n' }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = namespace(val='') %}
+    {%- if message.content is string %}
+        {%- set content.val = message.content %}
+    {%- else %}
+        {%- if message.content is iterable %}
+            {%- for entry in message.content %}
+                {%- if entry.type== 'text' %}
+                    {%- if content.val != '' %}
+                        {%- set content.val = content.val + '\n' %}
+                    {%- endif %}
+                    {%- set content.val = content.val + entry.text %}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+    {%- endif %}
+    {%- if (message.role == 'user') or (message.role == 'system' and not loop.first) %}
+        {{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val + '<|end_of_text|>\n' }}
+    {%- elif message.role == 'assistant' %}
+        {{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val }}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content.val) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|end_of_text|>\n' }}
+    {%- elif message.role == 'tool' %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != 'tool') %}
+            {{- '<|start_of_role|>user<|end_of_role|>' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content.val }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != 'tool') %}
+            {{- '<|end_of_text|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_of_role|>assistant<|end_of_role|>' }}
+{%- endif %}

answerability/granite-4.0-micro/alora/io.yaml

@@ -0,0 +1,25 @@
+# Model name string, or null to use whatever is provided in the chat completion request.
+model: ~
+# JSON schema of the model's output
+response_format: |
+  {
+    "type": "string",
+    "enum": ["answerable", "unanswerable"]
+  }
+transformations:
+  # Convert categorical answer to continuous value by decoding logprobs
+  - type: likelihood
+    categories_to_values:
+      "answerable": 1.0
+      "unanswerable": 0.0
+    input_path: []
+  # Convert scalar value to a record for consistency with other intrinsics
+  - type: nest
+    input_path: []
+    field_name: "answerability_likelihood"
+instruction: ~
+parameters:
+  # "unanswerable" can be 6 tokens at high temperatures
+  max_completion_tokens: 6
+# No sentence boundary detection
+sentence_boundaries: ~

answerability/granite-4.0-micro/alora/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>",
+  "unk_token": {
+    "content": "<|unk|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

answerability/granite-4.0-micro/alora/tokenizer_config.json

@@ -0,0 +1,783 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100256": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100257": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100261": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100262": {
+      "content": "<|filename|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100263": {
+      "content": "<|reponame|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100264": {
+      "content": "<|start_of_role|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|end_of_role|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<|unused_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100267": {
+      "content": "<|start_of_plugin|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100268": {
+      "content": "<|end_of_plugin|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100269": {
+      "content": "<|unk|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100270": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100271": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100272": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100273": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100274": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100275": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100276": {
+      "content": "<think_on>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100277": {
+      "content": "<think_off>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100278": {
+      "content": "<schema>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100279": {
+      "content": "</schema>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100280": {
+      "content": "<tools>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100281": {
+      "content": "</tools>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100282": {
+      "content": "<documents>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100283": {
+      "content": "</documents>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100284": {
+      "content": "<|unused_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100285": {
+      "content": "<|unused_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100286": {
+      "content": "<|unused_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100287": {
+      "content": "<|unused_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100288": {
+      "content": "<|unused_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100289": {
+      "content": "<|unused_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100290": {
+      "content": "<|unused_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100291": {
+      "content": "<|unused_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100292": {
+      "content": "<|unused_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100293": {
+      "content": "<|unused_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100294": {
+      "content": "<|unused_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100295": {
+      "content": "<|unused_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100296": {
+      "content": "<|unused_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100297": {
+      "content": "<|unused_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100298": {
+      "content": "<|unused_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100299": {
+      "content": "<|unused_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100300": {
+      "content": "<|unused_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100301": {
+      "content": "<|unused_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100302": {
+      "content": "<|unused_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100303": {
+      "content": "<|unused_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100304": {
+      "content": "<|unused_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100305": {
+      "content": "<|unused_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100306": {
+      "content": "<|unused_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100307": {
+      "content": "<|unused_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100308": {
+      "content": "<|unused_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100309": {
+      "content": "<|unused_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100310": {
+      "content": "<|unused_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100311": {
+      "content": "<|unused_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100312": {
+      "content": "<|unused_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100313": {
+      "content": "<|unused_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100314": {
+      "content": "<|unused_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100315": {
+      "content": "<|unused_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100316": {
+      "content": "<|unused_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100317": {
+      "content": "<|unused_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100318": {
+      "content": "<|unused_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100319": {
+      "content": "<|unused_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100320": {
+      "content": "<|unused_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100321": {
+      "content": "<|unused_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100322": {
+      "content": "<|unused_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100323": {
+      "content": "<|unused_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100324": {
+      "content": "<|unused_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100325": {
+      "content": "<|unused_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100326": {
+      "content": "<|unused_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100327": {
+      "content": "<|unused_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100328": {
+      "content": "<|unused_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100329": {
+      "content": "<|unused_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100330": {
+      "content": "<|unused_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100331": {
+      "content": "<|unused_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100332": {
+      "content": "<|unused_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100333": {
+      "content": "<|unused_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100334": {
+      "content": "<|unused_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100335": {
+      "content": "<|unused_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100336": {
+      "content": "<|unused_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100337": {
+      "content": "<|unused_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100338": {
+      "content": "<|unused_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100339": {
+      "content": "<|unused_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100340": {
+      "content": "<|unused_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100341": {
+      "content": "<|unused_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100342": {
+      "content": "<|unused_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100343": {
+      "content": "<|unused_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100344": {
+      "content": "<|unused_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100345": {
+      "content": "<|unused_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100346": {
+      "content": "<|unused_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100347": {
+      "content": "<|unused_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100348": {
+      "content": "<|unused_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100349": {
+      "content": "<|unused_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100350": {
+      "content": "<|unused_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100351": {
+      "content": "<|unused_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|end_of_text|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|end_of_text|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|unk|>"
+}

answerability/granite-4.0-micro/lora/README.md

@@ -0,0 +1,209 @@
+---
+base_model: ibm-granite/granite-4.0-micro
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:ibm-granite/granite-4.0-micro
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.2.dev0

answerability/granite-4.0-micro/lora/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "ibm-granite/granite-4.0-micro",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.17.2.dev0@UNKNOWN",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

answerability/granite-4.0-micro/lora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e79712fb2ca031723f1d1622bfb1781d81860bcefba08563a7d64052c346e48
+size 57703888

answerability/granite-4.0-micro/lora/chat_template.jinja

@@ -0,0 +1,118 @@
+{%- set tools_system_message_prefix = 'You are a helpful assistant with access to the following tools. You may call one or more tools to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>'  %}
+{%- set tools_system_message_suffix = '\n</tools>\n\nFor each tool call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.' %}
+{%- set documents_system_message_prefix = 'You are a helpful assistant with access to the following documents. You may use one or more documents to assist with the user query.\n\nYou are given a list of documents within <documents></documents> XML tags:\n<documents>' %}
+{%- set documents_system_message_suffix = '\n</documents>\n\nWrite the response to the user\'s input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.' %}
+{%- set g4_default_system_message = 'You are a helpful assistant. Please ensure responses are professional, accurate, and safe.' %}
+{%- if available_tools is defined and available_tools %}
+    {%- set tools = available_tools %}
+{%- endif %}
+{%- set ns = namespace(tools_system_message=tools_system_message_prefix,
+                       documents_system_message=documents_system_message_prefix,
+                       default_system_message=g4_default_system_message,
+                       system_message=''
+                       ) %}
+{%- if tools %}
+    {%- for tool in tools %}
+        {%- set ns.tools_system_message = ns.tools_system_message + '\n' + (tool | tojson) %}
+    {%- endfor %}
+    {%- set ns.tools_system_message = ns.tools_system_message + tools_system_message_suffix %}
+{%- else %}
+    {%- set ns.tools_system_message = '' %}
+{%- endif %}
+{%- if documents %}
+    {%- for document in documents %}
+        {%- set ns.documents_system_message = ns.documents_system_message + '\n' + (document | tojson) %}
+    {%- endfor %}
+    {%- set ns.documents_system_message = ns.documents_system_message + documents_system_message_suffix %}
+{%- else %}
+    {%- set ns.documents_system_message = '' %}
+{%- endif %}
+{%- if messages[0].role == 'system' %}
+    {%- if messages[0].content is string %}
+        {%- set ns.system_message = messages[0].content %}
+    {%- elif messages[0].content is iterable %}
+        {%- for entry in messages[0].content %}
+            {%- if entry.type== 'text' %}
+                {%- if ns.system_message != '' %}
+                    {%- set ns.system_message = ns.system_message + '\n' %}
+                {%- endif %}
+                {%- set ns.system_message = ns.system_message + entry.text %}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+    {%- if tools and documents %}
+        {%- set ns.system_message = ns.system_message + '\n\n' +  ns.tools_system_message + '\n\n' + ns.documents_system_message %}
+    {%- elif tools %}
+        {%- set ns.system_message = ns.system_message + '\n\n' + ns.tools_system_message %}
+    {%- elif documents %}
+        {%- set ns.system_message = ns.system_message + '\n\n' + ns.documents_system_message %}
+    {%- endif %}
+{%- else %}
+    {%- if tools and documents %}
+        {%- set ns.system_message = ns.tools_system_message + '\n\n' + ns.documents_system_message  %}
+    {%- elif tools %}
+        {%- set ns.system_message = ns.tools_system_message %}
+    {%- elif documents %}
+        {%- set ns.system_message = ns.documents_system_message %}
+    {%- endif %}
+{%- endif %}
+{%- if ns.system_message %}
+    {{- '<|start_of_role|>system<|end_of_role|>' + ns.system_message + '<|end_of_text|>\n' }}
+{%- else %}
+    {{- '<|start_of_role|>system<|end_of_role|>' + ns.default_system_message + '<|end_of_text|>\n' }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = namespace(val='') %}
+    {%- if message.content is string %}
+        {%- set content.val = message.content %}
+    {%- else %}
+        {%- if message.content is iterable %}
+            {%- for entry in message.content %}
+                {%- if entry.type== 'text' %}
+                    {%- if content.val != '' %}
+                        {%- set content.val = content.val + '\n' %}
+                    {%- endif %}
+                    {%- set content.val = content.val + entry.text %}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+    {%- endif %}
+    {%- if (message.role == 'user') or (message.role == 'system' and not loop.first) %}
+        {{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val + '<|end_of_text|>\n' }}
+    {%- elif message.role == 'assistant' %}
+        {{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val }}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content.val) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|end_of_text|>\n' }}
+    {%- elif message.role == 'tool' %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != 'tool') %}
+            {{- '<|start_of_role|>user<|end_of_role|>' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content.val }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != 'tool') %}
+            {{- '<|end_of_text|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_of_role|>assistant<|end_of_role|>' }}
+{%- endif %}

answerability/granite-4.0-micro/lora/io.yaml

@@ -0,0 +1,25 @@
+# Model name string, or null to use whatever is provided in the chat completion request.
+model: ~
+# JSON schema of the model's output
+response_format: |
+  {
+    "type": "string",
+    "enum": ["answerable", "unanswerable"]
+  }
+transformations:
+  # Convert categorical answer to continuous value by decoding logprobs
+  - type: likelihood
+    categories_to_values:
+      "answerable": 1.0
+      "unanswerable": 0.0
+    input_path: []
+  # Convert scalar value to a record for consistency with other intrinsics
+  - type: nest
+    input_path: []
+    field_name: "answerability_likelihood"
+instruction: ~
+parameters:
+  # "unanswerable" can be 6 tokens at high temperatures
+  max_completion_tokens: 6
+# No sentence boundary detection
+sentence_boundaries: ~

answerability/granite-4.0-micro/lora/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>",
+  "unk_token": {
+    "content": "<|unk|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

answerability/granite-4.0-micro/lora/tokenizer_config.json

@@ -0,0 +1,783 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100256": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100257": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100261": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100262": {
+      "content": "<|filename|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100263": {
+      "content": "<|reponame|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100264": {
+      "content": "<|start_of_role|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|end_of_role|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<|unused_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100267": {
+      "content": "<|start_of_plugin|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100268": {
+      "content": "<|end_of_plugin|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100269": {
+      "content": "<|unk|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100270": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100271": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100272": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100273": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100274": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100275": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100276": {
+      "content": "<think_on>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100277": {
+      "content": "<think_off>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100278": {
+      "content": "<schema>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100279": {
+      "content": "</schema>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100280": {
+      "content": "<tools>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100281": {
+      "content": "</tools>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100282": {
+      "content": "<documents>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100283": {
+      "content": "</documents>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100284": {
+      "content": "<|unused_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100285": {
+      "content": "<|unused_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100286": {
+      "content": "<|unused_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100287": {
+      "content": "<|unused_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100288": {
+      "content": "<|unused_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100289": {
+      "content": "<|unused_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100290": {
+      "content": "<|unused_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100291": {
+      "content": "<|unused_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100292": {
+      "content": "<|unused_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100293": {
+      "content": "<|unused_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100294": {
+      "content": "<|unused_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100295": {
+      "content": "<|unused_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100296": {
+      "content": "<|unused_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100297": {
+      "content": "<|unused_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100298": {
+      "content": "<|unused_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100299": {
+      "content": "<|unused_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100300": {
+      "content": "<|unused_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100301": {
+      "content": "<|unused_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100302": {
+      "content": "<|unused_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100303": {
+      "content": "<|unused_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100304": {
+      "content": "<|unused_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100305": {
+      "content": "<|unused_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100306": {
+      "content": "<|unused_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100307": {
+      "content": "<|unused_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100308": {
+      "content": "<|unused_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100309": {
+      "content": "<|unused_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100310": {
+      "content": "<|unused_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100311": {
+      "content": "<|unused_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100312": {
+      "content": "<|unused_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100313": {
+      "content": "<|unused_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100314": {
+      "content": "<|unused_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100315": {
+      "content": "<|unused_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100316": {
+      "content": "<|unused_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100317": {
+      "content": "<|unused_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100318": {
+      "content": "<|unused_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100319": {
+      "content": "<|unused_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100320": {
+      "content": "<|unused_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100321": {
+      "content": "<|unused_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100322": {
+      "content": "<|unused_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100323": {
+      "content": "<|unused_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100324": {
+      "content": "<|unused_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100325": {
+      "content": "<|unused_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100326": {
+      "content": "<|unused_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100327": {
+      "content": "<|unused_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100328": {
+      "content": "<|unused_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100329": {
+      "content": "<|unused_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100330": {
+      "content": "<|unused_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100331": {
+      "content": "<|unused_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100332": {
+      "content": "<|unused_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100333": {
+      "content": "<|unused_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100334": {
+      "content": "<|unused_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100335": {
+      "content": "<|unused_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100336": {
+      "content": "<|unused_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100337": {
+      "content": "<|unused_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100338": {
+      "content": "<|unused_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100339": {
+      "content": "<|unused_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100340": {
+      "content": "<|unused_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100341": {
+      "content": "<|unused_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100342": {
+      "content": "<|unused_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100343": {
+      "content": "<|unused_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100344": {
+      "content": "<|unused_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100345": {
+      "content": "<|unused_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100346": {
+      "content": "<|unused_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100347": {
+      "content": "<|unused_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100348": {
+      "content": "<|unused_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100349": {
+      "content": "<|unused_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100350": {
+      "content": "<|unused_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100351": {
+      "content": "<|unused_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|end_of_text|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|end_of_text|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|unk|>"
+}

answerability/granite4_micro/alora/io.yaml

@@ -0,0 +1,25 @@
+model: null
+response_format: null
+transformations:
+- type: likelihood
+  categories_to_values:
+    answerable: 1.0
+    unanswerable: 0.0
+  input_path: []
+- type: nest
+  input_path: []
+  field_name: answerability_likelihood
+instruction: null
+parameters:
+  response_format:
+    type: json_schema
+    json_schema:
+      schema:
+        type: string
+        enum:
+        - answerable
+        - unanswerable
+      strict: true
+  max_tokens: 6
+sentence_boundaries: null
+docs_as_message: roles

answerability/granite4_micro/lora/Lora-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88a80717c357a5165b249ba0350b00e09605597db74686430d3c924ca36c9184
+size 15335776

answerability/granite4_micro/lora/Modelfile

@@ -0,0 +1,2 @@
+FROM granite4:micro
+ADAPTER Lora-q8_0.gguf

answerability/granite4_micro/lora/io.yaml

@@ -0,0 +1,25 @@
+model: null
+response_format: null
+transformations:
+- type: likelihood
+  categories_to_values:
+    answerable: 1.0
+    unanswerable: 0.0
+  input_path: []
+- type: nest
+  input_path: []
+  field_name: answerability_likelihood
+instruction: null
+parameters:
+  response_format:
+    type: json_schema
+    json_schema:
+      schema:
+        type: string
+        enum:
+        - answerable
+        - unanswerable
+      strict: true
+  max_tokens: 6
+sentence_boundaries: null
+docs_as_message: roles

citations/README.md

@@ -0,0 +1,245 @@
+---
+license: apache-2.0
+language:
+- en
+pipeline_tag: text-generation
+library_name: peft
+library_name: transformers
+---
+
+# Citation Generation Intrinsic
+
+## Model Summary 
+
+This is a RAG-specific intrinsic fine-tuned for the citation generation task. Given a multi-turn conversation between a user and an AI assistant ending with an assistant response and a set of documents/passages on which the last assistant response is supposed to be based, the intrinsic generates citations for the last assistant response from the provided documents/passages. The citation generation intrinsic has the following features:
+1. **Fine-grained citations:** The intrinsic generates citations for each sentence of the assistant response (when available). Each citation consists of a set of sentences from the documents/passages that support the corresponding sentence in the assistant response.   
+2. **Post-hoc citation generation:** Since the intrinsic takes the assistant response as input, it can generate citations for responses generated by any LLM. Pick your favorite LLM for response generation and use the citation generation intrinsic to generate post-hoc citations!
+
+We have created two implementation of the intrinsic as LoRA adapters trained over granite-4.0-micro and gpt-oss-20b, respectively. This is the model card for the LoRA adapter trained over granite-4.0-micro. The model card for the LoRA adapter trained over gpt-oss-20b can be found [here](https://huggingface.co/ibm-granite/granitelib-rag-gpt-oss-r1.0/blob/main/citations/README.md). 
+
+- **Developer:** IBM Research
+- **Model type:** LoRA adapter for [ibm-granite/granite-4.0-micro](https://huggingface.co/ibm-granite/granite-4.0-micro)
+- **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)
+
+## Intended use
+This is a citation generation intrinsic that gives the ability to generate citations for the last assistant response in a multi-turn RAG conversation based on a set of provided documents/passages. It can be used to generate post-hoc citations for assistant responses generated by any LLM in a RAG setting.  
+
+> [!TIP]  
+> Note: While you can invoke the citation generation intrinsic directly, it is strongly recommended to call it through the [Mellea](https://mellea.ai) framework, which wraps the model with a tailored I/O processor, enabling a friendlier development interface. We next describe the input/output of the citation generation intrinsic when invoked through Mellea.
+
+**Intrinsic input**: The citation generation intrinsic takes as input the following:
+- _Conversation:_ A list of conversational turns ending with the last user question, encoded as a list of user/assistant messages.
+- _Assistant response:_ The assistant response to the last user question, which is also the response for which citations will be generated, provided as a string.
+- _Documents:_ A list of documents from which the citations should be drawn, encoded as a collection of Document objects.
+
+**Intrinsic output**: The output of the citation generation intrinsic contains the citations for the last assistant response. The citations are provided in the form of a JSON array, whose items include the text and begin/end of a response span together with the text, document id and begin/end of a document span that serves as a citation for that response span. When there are more than one document spans that serve as citations for a single response span, they are represented as separate objects in the JSON array.
+
+**Going from input to output**: When calling the intrinsic through Mellea, the framework internally performs multiple steps to transform the intrinsic input to the corresponding output. While you do not have to explicitly invoke these steps, we next provide a brief overview of this process. Given an input to the citation generation intrinsic, Mellea performs the following tasks:
+- _Convert user input to the appropriate format expected by the underlying citation generation model._ This includes, among others, splitting the last assistant response and the documents into sentences and prepending them with sentence IDs as well as introducing an appropriate task-specific instruction.
+- _Call underlying citation generation model for inference._ The model generates citations using a compact representation consisting of sentence IDs in the last assistant response and documents.
+- _Convert model output to final output._ The low-level raw model output is converted to the final output by, among others, mapping the sentence IDs back to response and document spans. The result is an application-friendly JSON format ready for consumption by downstream applications. 
+
+## Example
+
+You can find below an example of the input and corresponding output of the citations generation intrinsic:
+
+### Input
+
+**Conversation:**
+
+User: What is the visibility level of Git Repos and Issue Tracking projects?
+
+**Assistant response:**
+
+Git Repos and Issue Tracking projects can have one of the following visibility levels: private, internal, or public. Private projects are visible only to project members, internal projects are visible to all users that are logged in to IBM Cloud, and public projects are visible to anyone. By default, new projects are set to private visibility level, which is the most secure for your data.
+
+**Documents:**
+
+Git Repos and Issue Tracking is an IBM-hosted component of the Continuous Delivery service. All of the data that you provide to Git Repos and Issue Tracking, including but not limited to source files, issues, pull requests, and project configuration properties, is managed securely within Continuous Delivery. However, Git Repos and Issue Tracking supports various mechanisms for exporting, sending, or otherwise sharing data to users and third parties. The ability of Git Repos and Issue Tracking to share information is typical of many social coding platforms. However, such sharing might conflict with regulatory controls that apply to your business. After you create a project in Git Repos and Issue Tracking, but before you entrust any files, issues, records, or other data with the project, review the project settings and change any settings that you deem necessary to protect your data. Settings to review include visibility levels, email notifications, integrations, web hooks, access tokens, deploy tokens, and deploy keys. Project visibility levels \n\nGit Repos and Issue Tracking projects can have one of the following visibility levels: private, internal, or public. * Private projects are visible only to project members. This setting is the default visibility level for new projects, and is the most secure visibility level for your data. * Internal projects are visible to all users that are logged in to IBM Cloud. * Public projects are visible to anyone. To limit project access to only project members, complete the following steps:\n\n\n\n1. From the project sidebar, click Settings > General. 2. On the General Settings page, click Visibility > project features > permissions. 3. Locate the Project visibility setting. 4. Select Private, if it is not already selected. 5. Click Save changes. Project membership \n\nGit Repos and Issue Tracking is a cloud hosted social coding environment that is available to all Continuous Delivery users. If you are a Git Repos and Issue Tracking project Maintainer or Owner, you can invite any user and group members to the project. IBM Cloud places no restrictions on who you can invite to a project.
+
+### Output
+
+```json
+[
+    {
+        "response_begin": 0,
+        "response_end": 117,
+        "response_text": "Git Repos and Issue Tracking projects can have one of the following visibility levels: private, internal, or public. ",
+        "citation_doc_id": "1",
+        "citation_begin": 1034,
+        "citation_end": 1179,
+        "citation_text": "Project visibility levels \n\nGit Repos and Issue Tracking projects can have one of the following visibility levels: private, internal, or public. "
+    },
+    {
+        "response_begin": 117,
+        "response_end": 290,
+        "response_text": "Private projects are visible only to project members, internal projects are visible to all users that are logged in to IBM Cloud, and public projects are visible to anyone. ",
+        "citation_doc_id": "1",
+        "citation_begin": 1179,
+        "citation_end": 1235,
+        "citation_text": "* Private projects are visible only to project members. "
+    },
+    {
+        "response_begin": 117,
+        "response_end": 290,
+        "response_text": "Private projects are visible only to project members, internal projects are visible to all users that are logged in to IBM Cloud, and public projects are visible to anyone. ",
+        "citation_doc_id": "1",
+        "citation_begin": 1353,
+        "citation_end": 1472,
+        "citation_text": "* Internal projects are visible to all users that are logged in to IBM Cloud. * Public projects are visible to anyone. "
+    },
+    {
+        "response_begin": 290,
+        "response_end": 391,
+        "response_text": "By default, new projects are set to private visibility level, which is the most secure for your data.",
+        "citation_doc_id": "1",
+        "citation_begin": 1235,
+        "citation_end": 1353,
+        "citation_text": "This setting is the default visibility level for new projects, and is the most secure visibility level for your data. "
+    }
+]
+```
+
+## Quickstart
+
+The recommended way to call this intrinsic is through the [Mellea](https://mellea.ai) framework. For code snippets demonstrating how to use this and other intrinsics, please refer to the [Mellea intrinsics examples](https://github.com/generative-computing/mellea/tree/main/docs/examples/intrinsics).
+
+## Evaluation
+
+We evaluated the citation generation intrinsic on a revised version of the [LongBench-Cite](https://arxiv.org/abs/2409.02897) benchmark; a benchmark evaluating the ability of models to produce fine-grained span-level citations (i.e., identify the spans within the input documents/passages that support a statement in the response) with a focus on long contexts. Being originally designed to evaluate inline citation generation approaches (i.e., approaches generating the assistant response and the citations at the same time), we adapt the benchmark for the evaluation of post-hoc citation generation (where citations are generated for a given assistant response generated by an upstream model).
+
+For the following experiments, we prompted Llama-3.1-70B-Instruct to generate the assistant response for the LongBench-Cite tasks. Then, two types of models were asked to create citations for these responses:
+- _Citation generation LoRA adapters:_ These are the two citation generation LoRA adapter implementations of the citation intrinsic, as described above.
+- _Prompt-based baselines:_ These are out-of-the-box LLMs prompted to generate post-hoc citations for the given assistant responses. Prompting was performed through a version of the 1-shot prompt used in the original benchmark, adapted for post-hoc citation generation.
+
+The evaluation results are shown in the table below:
+
+<table>
+<tr>
+    <th>Model</th>
+    <th colspan="3">Longbench-Chat (en)</th>
+    <th colspan="3">MultifieldQA (en)</th>
+    <th colspan="3">HotpotQA</th>
+    <th colspan="3">GovReport</th>
+    <th>AVG F1</th>
+</tr>
+<tr>
+    <th></th>
+    <th>R</th><th>P</th><th>F1</th>
+    <th>R</th><th>P</th><th>F1</th>
+    <th>R</th><th>P</th><th>F1</th>
+    <th>R</th><th>P</th><th>F1</th>
+    <th></th>
+</tr>
+<tr>
+    <th colspan="14" style="background-color: #f5f5f5;">Citation Generation LoRA Adapters</th>
+</tr>
+<tr>
+    <td>granite-4.0-micro LoRA</td>
+    <td>42.7</td><td>46.5</td><td>41.4</td>
+    <td>68.5</td><td>81.1</td><td>72.0</td>
+    <td>62.9</td><td>67.9</td><td>61.0</td>
+    <td>70.2</td><td>79.3</td><td>74.1</td>
+    <td><b>62.1</b></td>
+</tr>
+<tr>
+    <td>gpt-oss-20b LoRA</td>
+    <td>56.1</td><td>61.4</td><td>55.3</td>
+    <td>71.6</td><td>87.1</td><td>76.8</td>
+    <td>69.9</td><td>71.5</td><td>66.1</td>
+    <td>73.8</td><td>84.8</td><td>78.2</td>
+    <td><b>69.1</b></td>
+</tr>
+<tr>
+    <th></th>
+    <th></th><th></th><th></th>
+    <th></th><th></th><th></th>
+    <th></th><th></th><th></th>
+    <th></th><th></th><th></th>
+    <th></th>
+</tr>
+<tr>
+    <th colspan="14" style="background-color: #f5f5f5;">Prompting-based Baselines</th>
+</tr>
+<tr>
+    <td>granite-4.0-micro Prompted</td>
+    <td>5.4</td><td>6.1</td><td>3.5</td>
+    <td>22.3</td><td>32.1</td><td>22.3</td>
+    <td>18.0</td><td>21.4</td><td>14.2</td>
+    <td>8.9</td><td>18.0</td><td>10.1</td>
+    <td><b>12.5</b></td>
+</tr>
+<tr>
+    <td>gpt-oss-20b Prompted</td>
+    <td>38.0</td><td>38.7</td><td>34.7</td>
+    <td>56.8</td><td>68.1</td><td>59.5</td>
+    <td>54.0</td><td>60.4</td><td>52.2</td>
+    <td>48.3</td><td>59.2</td><td>52.4</td>
+    <td><b>49.7</b></td>
+</tr>
+<tr>
+    <td>gpt-oss-120b Prompted</td>
+    <td>46.4</td><td>49.1</td><td>45.2</td>
+    <td>68.9</td><td>76.6</td><td>70.1</td>
+    <td>65.4</td><td>66.5</td><td>62.2</td>
+    <td>70.8</td><td>75.4</td><td>72.2</td>
+    <td><b>62.4</b></td>
+</tr>
+<tr>
+    <td>gpt-4o Prompted</td>
+    <td>56.9</td><td>60.1</td><td>56.2</td>
+    <td>68.7</td><td>79.6</td><td>71.4</td>
+    <td>65.3</td><td>73.6</td><td>65.3</td>
+    <td>74.3</td><td>81.5</td><td>76.9</td>
+    <td><b>67.5</b></td>
+</tr>
+
+</table>
+
+We observe that both citation generation LoRA adapters perform better not only than the corresponding base models prompted out of the box but also better than bigger models. For instance, the granite-4.0-micro LoRA performs on par with prompting the significantly larger gpt-oss-120b. Similarly, the gpt-oss-20b LoRA outperforms prompting the much larger gpt-4o.
+
+Notes:
+- The evaluation results are reported on the English subset of LongBench-Cite (i.e., restricted to instances whose `language` field equals to `en`).
+- To generate the assistant responses fed to all evaluated models, we prompted Llama-3.1-70B-Instruct using the one-shot prompt described in the LongBench-Cite paper (which asks the model to generate a grounded response with citations) and removed the citations in post-processing.
+- The AVG F1 column contains the average of the four dataset-specific F1 scores.
+
+## Training Details
+
+The citation generation intrinsic was trained on synthetically-generated citation datasets. The process of generating the training data consisted of two main steps:
+- _Multi-turn RAG conversation generation:_ Starting from publicly available document corpora, we generated a set of multi-turn RAG data, consisting of multi-turn conversations grounded on passages retrieved from the corpora. For details on the RAG conversation generation process please refer to the [Granite Technical Report](https://github.com/ibm-granite/granite-3.0-language-models/blob/main/paper.pdf) and [Lee, Young-Suk, et al.](https://arxiv.org/pdf/2409.11500)
+- _Citation generation:_ For each turn of the multi-turn RAG conversations from the previous step, we used a multi-step synthetic citation generation pipeline to generate citations for the assistant response.
+
+The resulting data instances were used to train the citation generation intrinsic.
+
+### Training Data
+
+The following public datasets were used as seed datasets for the multi-turn RAG conversation generation process:
+- [MultiDoc2Dial](https://huggingface.co/datasets/IBM/multidoc2dial)
+- [QuAC](https://huggingface.co/datasets/allenai/quac)
+
+### Adapter Details
+
+| Property | LoRA |
+|---|---|
+| **Base Model** | ibm-granite/granite-4.0-micro |
+| **PEFT Type** | LORA |
+| **Rank (r)** | 16 |
+| **Alpha** | 32 |
+| **Target Modules** | q_proj, k_proj, v_proj, o_proj |
+
+**Infrastructure:**
+We trained the citation generation granite-4.0-micro LoRA adapter on IBM's Vela cluster using 8 A100 GPUs.
+
+**Ethical Considerations & Limitations:**
+The model's outputs are not guaranteed to be factually accurate or complete. All outputs should be independently validated before use in decision-making or downstream applications. The model has been trained and evaluated on English data only.
+
+## Resources
+
+- ⭐️ Learn about the latest updates with Granite: https://www.ibm.com/granite
+- 📄 Get started with tutorials, best practices, and prompt engineering advice: https://www.ibm.com/granite/docs/
+- 💡 Learn about the latest Granite learning resources: https://github.com/ibm-granite/granite-guardian/tree/main/cookbooks
+
+## Model Card Authors 
+
+[Yannis Katsis](mailto:yannis.katsis@ibm.com)</br>
+[Chulaka Gunasekara](mailto:chulaka.gunasekara@ibm.com)

citations/granite-3.3-8b-instruct/alora/README.md

@@ -0,0 +1,209 @@
+---
+base_model: ibm-granite/granite-3.3-8b-instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:ibm-granite/granite-3.3-8b-instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.2.dev0

citations/granite-3.3-8b-instruct/alora/adapter_config.json

@@ -0,0 +1,44 @@
+{
+  "alora_invocation_tokens": [
+    49152,
+    17594,
+    49153
+  ],
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "ibm-granite/granite-3.3-8b-instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

citations/granite-3.3-8b-instruct/alora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bbc508c5be778ee9cc445430752355d0351aa9a3531349ba0a2ad805e194ab2
+size 94404160

citations/granite-3.3-8b-instruct/alora/added_tokens.json

@@ -0,0 +1,9 @@
+{
+  "<|end_of_cite|>": 49156,
+  "<|end_of_plugin|>": 49158,
+  "<|end_of_role|>": 49153,
+  "<|start_of_cite|>": 49155,
+  "<|start_of_plugin|>": 49157,
+  "<|start_of_role|>": 49152,
+  "<|tool_call|>": 49154
+}

citations/granite-3.3-8b-instruct/alora/chat_template.jinja

@@ -0,0 +1,62 @@
+{# Alias tools -> available_tools #}
+{%- if tools and not available_tools -%}
+    {%- set available_tools = tools -%}
+{%- endif -%}
+{%- if messages[0]['role'] == 'system' %}
+     {%- set system_message = messages[0]['content'] %}
+     {%- set loop_messages = messages[1:] %}
+ {%- else %}
+     {%- set system_message = "Knowledge Cutoff Date: April 2024.
+Today's Date: " + strftime_now('%B %d, %Y') + ".
+You are Granite, developed by IBM." %}
+     {%- if available_tools and documents %}
+         {%- set system_message = system_message + " You are a helpful assistant with access to the following tools. When a tool is required to answer the user's query, respond only with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.
+Write the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data." %}
+     {%- elif available_tools %}
+         {%- set system_message = system_message + " You are a helpful assistant with access to the following tools. When a tool is required to answer the user's query, respond only with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request." %}
+     {%- elif documents %}
+         {%- set system_message = system_message + " Write the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data." %}
+    {%- elif thinking %}
+    {%- set system_message = system_message + " You are a helpful AI assistant.
+Respond to every user query in a comprehensive and detailed way. You can write down your thoughts and reasoning process before responding. In the thought process, engage in a comprehensive cycle of analysis, summarization, exploration, reassessment, reflection, backtracing, and iteration to develop well-considered thinking process. In the response section, based on various attempts, explorations, and reflections from the thoughts section, systematically present the final solution that you deem correct. The response should summarize the thought process. Write your thoughts between <think></think> and write your response between <response></response> for each user query." %}
+     {%- else %}
+         {%- set system_message = system_message + " You are a helpful AI assistant." %}
+     {%- endif %}
+     {%- if 'citations' in controls and documents %}
+         {%- set system_message = system_message + '
+Use the symbols <|start_of_cite|> and <|end_of_cite|> to indicate when a fact comes from a document in the search result, e.g <|start_of_cite|> {document_id: 1}my fact <|end_of_cite|> for a fact from document 1. Afterwards, list all the citations with their corresponding documents in an ordered list.' %}
+     {%- endif %}
+     {%- if 'hallucinations' in controls and documents %}
+         {%- set system_message = system_message + '
+Finally, after the response is written, include a numbered list of sentences from the response with a corresponding risk value that are hallucinated and not based in the documents.' %}
+     {%- endif %}
+     {%- set loop_messages = messages %}
+ {%- endif %}
+ {{- '<|start_of_role|>system<|end_of_role|>' + system_message + '<|end_of_text|>
+' }}
+ {%- if available_tools %}
+     {{- '<|start_of_role|>available_tools<|end_of_role|>' }}
+     {{- available_tools | tojson(indent=4) }}
+     {{- '<|end_of_text|>
+' }}
+ {%- endif %}
+ {%- if documents %}
+     {%- for document in documents %}
+         {{- '<|start_of_role|>document {"document_id": "' + document['doc_id'] | string + '"}<|end_of_role|>
+' }}
+         {{- document['text'] }}
+         {{- '<|end_of_text|>
+' }}
+              {%- endfor %}
+ {%- endif %}
+ {%- for message in loop_messages %}
+     {{- '<|start_of_role|>' + message['role'] + '<|end_of_role|>' + message['content'] + '<|end_of_text|>
+' }}
+     {%- if loop.last and add_generation_prompt %}
+         {{- '<|start_of_role|>assistant' }}
+             {%- if controls %}
+                 {{- ' ' + controls | tojson()}}
+             {%- endif %}
+         {{- '<|end_of_role|>' }}
+     {%- endif %}
+ {%- endfor %}

citations/granite-3.3-8b-instruct/alora/special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    "<|start_of_role|>",
+    "<|end_of_role|>",
+    "<|tool_call|>",
+    "<|start_of_cite|>",
+    "<|end_of_cite|>",
+    "<|start_of_plugin|>",
+    "<|end_of_plugin|>"
+  ],
+  "bos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

citations/granite-3.3-8b-instruct/alora/tokenizer_config.json

@@ -0,0 +1,234 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49152": {
+      "content": "<|start_of_role|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49153": {
+      "content": "<|end_of_role|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49154": {
+      "content": "<|tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49155": {
+      "content": "<|start_of_cite|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49156": {
+      "content": "<|end_of_cite|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49157": {
+      "content": "<|start_of_plugin|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49158": {
+      "content": "<|end_of_plugin|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|start_of_role|>",
+    "<|end_of_role|>",
+    "<|tool_call|>",
+    "<|start_of_cite|>",
+    "<|end_of_cite|>",
+    "<|start_of_plugin|>",
+    "<|end_of_plugin|>"
+  ],
+  "bos_token": "<|end_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 9223372036854775807,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|end_of_text|>",
+  "vocab_size": 49152
+}

citations/granite-3.3-8b-instruct/lora/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ibm-granite/granite-3.3-8b-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

citations/granite-3.3-8b-instruct/lora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4024cd8b4d6e256ddf5541fa2463c091463443b43d6d0aeb74d97ebeef8dc0be
+size 99034536