Instructions to use VoiceScribe/voicescribe-corrector with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use VoiceScribe/voicescribe-corrector with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="VoiceScribe/voicescribe-corrector")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("VoiceScribe/voicescribe-corrector")
model = AutoModelForCausalLM.from_pretrained("VoiceScribe/voicescribe-corrector")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use VoiceScribe/voicescribe-corrector with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "VoiceScribe/voicescribe-corrector"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VoiceScribe/voicescribe-corrector",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/VoiceScribe/voicescribe-corrector

SGLang

How to use VoiceScribe/voicescribe-corrector with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "VoiceScribe/voicescribe-corrector" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VoiceScribe/voicescribe-corrector",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "VoiceScribe/voicescribe-corrector" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VoiceScribe/voicescribe-corrector",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use VoiceScribe/voicescribe-corrector with Docker Model Runner:
```
docker model run hf.co/VoiceScribe/voicescribe-corrector
```

Andrewsab commited on about 1 month ago

Commit

4ef73dc

verified ·

1 Parent(s): 9f121d9

Voice Scribe mirror corrector from anubhav200/Qwen3-4B-Instruct-2507-openvino-int4@ea34b26c6e5f

Browse files

Files changed (20) hide show

.gitattributes +1 -0
README.md +239 -0
UPSTREAM_SOURCE.md +53 -0
added_tokens.json +28 -0
chat_template.jinja +61 -0
config.json +68 -0
generation_config.json +13 -0
graph.pbtxt +37 -0
merges.txt +0 -0
openvino_detokenizer.bin +3 -0
openvino_detokenizer.xml +220 -0
openvino_model.bin +3 -0
openvino_model.xml +0 -0
openvino_tokenizer.bin +3 -0
openvino_tokenizer.xml +771 -0
special_tokens_map.json +31 -0
tokenizer.json +3 -0
tokenizer_config.json +239 -0
vocab.json +0 -0
voicescribe-model-layout.json +36 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* 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

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md ADDED Viewed

	@@ -0,0 +1,239 @@

+---
+library_name: transformers
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507/blob/main/LICENSE
+pipeline_tag: text-generation
+---
+# OpenVino Supported Model
+- *Supports*: NPU, GPU, CPU
+- *INT4*: True
+- *Sym*: True
+# Performance
+- Token Generation performance is b/w 8 to 16 Tokens per second on Intel 13 TOPS NPU. (Please make sure you have installed the latest NPU drivers from Intel, else performance won't be good.)
+## Instructions
+1. Make sure you have downloaded and install the latest NPU driver: https://www.intel.com/content/www/us/en/download/794734/871766/intel-npu-driver-windows.html. I am on version 32.0.100.4514.
+2. Create a folder where you would put all the openvino models, we will call it has root_folder.
+3. Download and Install OVMS if not already installed. Follow the instructions here to install OVMS: `https://docs.openvino.ai/2025/model-server/ovms_docs_deploying_server_baremetal.html`
+5. Start the model using this command, it would auto download the model and save it in the root_folder that you have provided.
+Example Command: (with root_folder C:\projects\vino-models)
+```
+ovms.exe --source_model "anubhav200/Qwen3-4B-Instruct-2507-openvino-int4" --model_repository_path  C:\projects\vino-models --rest_port 8000 --task text_generation --target_device NPU --cache_size 2 --max_prompt_len 4096
+```
+Command Vars:
+```
+ovms.exe --source_model "<model name>" --model_repository_path  <root_folder path> --rest_port 8000 --task text_generation --target_device NPU --cache_size 2 --max_prompt_len <N tokens>
+```
+# Qwen3-4B-Instruct-2507
+<a href="https://chat.qwen.ai" target="_blank" style="margin: 2px;">
+    <img alt="Chat" src="https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5" style="display: inline-block; vertical-align: middle;"/>
+</a>
+## Highlights
+We introduce the updated version of the **Qwen3-4B non-thinking mode**, named **Qwen3-4B-Instruct-2507**, featuring the following key enhancements:
+- **Significant improvements** in general capabilities, including **instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage**.
+- **Substantial gains** in long-tail knowledge coverage across **multiple languages**.
+- **Markedly better alignment** with user preferences in **subjective and open-ended tasks**, enabling more helpful responses and higher-quality text generation.
+- **Enhanced capabilities** in **256K long-context understanding**.
+![image/jpeg](https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3-2507/Qwen3-4B-Instruct.001.jpeg)
+## Model Overview
+**Qwen3-4B-Instruct-2507** has the following features:
+- Type: Causal Language Models
+- Training Stage: Pretraining & Post-training
+- Number of Parameters: 4.0B
+- Number of Paramaters (Non-Embedding): 3.6B
+- Number of Layers: 36
+- Number of Attention Heads (GQA): 32 for Q and 8 for KV
+- Context Length: **262,144 natively**.
+**NOTE: This model supports only non-thinking mode and does not generate ``<think></think>`` blocks in its output. Meanwhile, specifying `enable_thinking=False` is no longer required.**
+For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [blog](https://qwenlm.github.io/blog/qwen3/), [GitHub](https://github.com/QwenLM/Qwen3), and [Documentation](https://qwen.readthedocs.io/en/latest/).
+## Performance
+|  | GPT-4.1-nano-2025-04-14 | Qwen3-30B-A3B Non-Thinking | Qwen3-4B Non-Thinking | Qwen3-4B-Instruct-2507 |
+|--- | --- | --- | --- | --- |
+| **Knowledge** | | | |
+| MMLU-Pro | 62.8 | 69.1 | 58.0 | **69.6** |
+| MMLU-Redux | 80.2 | 84.1 | 77.3 | **84.2** |
+| GPQA | 50.3 | 54.8 | 41.7 | **62.0** |
+| SuperGPQA | 32.2 | 42.2 | 32.0 | **42.8** |
+| **Reasoning** | | | |
+| AIME25 | 22.7 | 21.6 | 19.1 | **47.4** |
+| HMMT25 | 9.7 | 12.0 | 12.1 | **31.0** |
+| ZebraLogic | 14.8 | 33.2 | 35.2 | **80.2** |
+| LiveBench 20241125 | 41.5 | 59.4 | 48.4 | **63.0** |
+| **Coding** | | | |
+| LiveCodeBench v6 (25.02-25.05) | 31.5 | 29.0 | 26.4 | **35.1** |
+| MultiPL-E | 76.3 | 74.6 | 66.6 | **76.8** |
+| Aider-Polyglot |  9.8 | **24.4** | 13.8 | 12.9 |
+| **Alignment** | | | |
+| IFEval | 74.5 | **83.7** | 81.2 | 83.4 |
+| Arena-Hard v2* | 15.9 | 24.8 | 9.5 | **43.4** |
+| Creative Writing v3 | 72.7 | 68.1 | 53.6 | **83.5** |
+| WritingBench | 66.9 | 72.2 | 68.5 | **83.4** |
+| **Agent** | | | |
+| BFCL-v3 | 53.0 | 58.6 | 57.6 | **61.9** |
+| TAU1-Retail | 23.5 | 38.3 | 24.3 | **48.7** |
+| TAU1-Airline | 14.0 | 18.0 | 16.0 | **32.0** |
+| TAU2-Retail | - | 31.6 | 28.1 | **40.4** |
+| TAU2-Airline | - | 18.0 | 12.0 | **24.0** |
+| TAU2-Telecom | - | **18.4** | 17.5 | 13.2 |
+| **Multilingualism** | | | |
+| MultiIF | 60.7 | **70.8** | 61.3 | 69.0 |
+| MMLU-ProX | 56.2 | **65.1** | 49.6 | 61.6 |
+| INCLUDE | 58.6 | **67.8** | 53.8 | 60.1 |
+| PolyMATH | 15.6 | 23.3 | 16.6 | **31.1** |
+*: For reproducibility, we report the win rates evaluated by GPT-4.1.
+## Quickstart
+The code of Qwen3 has been in the latest Hugging Face `transformers` and we advise you to use the latest version of `transformers`.
+With `transformers<4.51.0`, you will encounter the following error:
+```
+KeyError: 'qwen3'
+```
+The following contains a code snippet illustrating how to use the model generate content based on given inputs.
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+model_name = "Qwen/Qwen3-4B-Instruct-2507"
+# load the tokenizer and the model
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+# prepare the model input
+prompt = "Give me a short introduction to large language model."
+messages = [
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+# conduct text completion
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=16384
+)
+output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
+content = tokenizer.decode(output_ids, skip_special_tokens=True)
+print("content:", content)
+```
+For deployment, you can use `sglang>=0.4.6.post1` or `vllm>=0.8.5` or to create an OpenAI-compatible API endpoint:
+- SGLang:
+    ```shell
+    python -m sglang.launch_server --model-path Qwen/Qwen3-4B-Instruct-2507 --context-length 262144
+    ```
+- vLLM:
+    ```shell
+    vllm serve Qwen/Qwen3-4B-Instruct-2507 --max-model-len 262144
+    ```
+**Note: If you encounter out-of-memory (OOM) issues, consider reducing the context length to a shorter value, such as `32,768`.**
+For local use, applications such as Ollama, LMStudio, MLX-LM, llama.cpp, and KTransformers have also supported Qwen3.
+## Agentic Use
+Qwen3 excels in tool calling capabilities. We recommend using [Qwen-Agent](https://github.com/QwenLM/Qwen-Agent) to make the best use of agentic ability of Qwen3. Qwen-Agent encapsulates tool-calling templates and tool-calling parsers internally, greatly reducing coding complexity.
+To define the available tools, you can use the MCP configuration file, use the integrated tool of Qwen-Agent, or integrate other tools by yourself.
+```python
+from qwen_agent.agents import Assistant
+# Define LLM
+llm_cfg = {
+    'model': 'Qwen3-4B-Instruct-2507',
+    # Use a custom endpoint compatible with OpenAI API:
+    'model_server': 'http://localhost:8000/v1',  # api_base
+    'api_key': 'EMPTY',
+}
+# Define Tools
+tools = [
+    {'mcpServers': {  # You can specify the MCP configuration file
+            'time': {
+                'command': 'uvx',
+                'args': ['mcp-server-time', '--local-timezone=Asia/Shanghai']
+            },
+            "fetch": {
+                "command": "uvx",
+                "args": ["mcp-server-fetch"]
+            }
+        }
+    },
+  'code_interpreter',  # Built-in tools
+]
+# Define Agent
+bot = Assistant(llm=llm_cfg, function_list=tools)
+# Streaming generation
+messages = [{'role': 'user', 'content': 'https://qwenlm.github.io/blog/ Introduce the latest developments of Qwen'}]
+for responses in bot.run(messages=messages):
+    pass
+print(responses)
+```
+## Best Practices
+To achieve optimal performance, we recommend the following settings:
+1. **Sampling Parameters**:
+   - We suggest using `Temperature=0.7`, `TopP=0.8`, `TopK=20`, and `MinP=0`.
+   - For supported frameworks, you can adjust the `presence_penalty` parameter between 0 and 2 to reduce endless repetitions. However, using a higher value may occasionally result in language mixing and a slight decrease in model performance.
+2. **Adequate Output Length**: We recommend using an output length of 16,384 tokens for most queries, which is adequate for instruct models.
+3. **Standardize Output Format**: We recommend using prompts to standardize model outputs when benchmarking.
+   - **Math Problems**: Include "Please reason step by step, and put your final answer within \boxed{}." in the prompt.
+   - **Multiple-Choice Questions**: Add the following JSON structure to the prompt to standardize responses: "Please show your choice in the `answer` field with only the choice letter, e.g., `"answer": "C"`."
+### Citation
+If you find our work helpful, feel free to give us a cite.
+```
+@misc{qwen3technicalreport,
+      title={Qwen3 Technical Report},
+      author={Qwen Team},
+      year={2025},
+      eprint={2505.09388},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2505.09388},
+}
+```

UPSTREAM_SOURCE.md ADDED Viewed

	@@ -0,0 +1,53 @@

+# Voice Scribe Model Mirror
+This repository is a Voice Scribe distribution mirror. The model artifacts are
+copied from the upstream repository and the source revision below is pinned.
+| Field | Value |
+| --- | --- |
+| Layout key | `corrector` |
+| Target directory in installer | `qwen3-4b-instruct-2507-ov` |
+| Upstream repo | `anubhav200/Qwen3-4B-Instruct-2507-openvino-int4` |
+| Upstream revision | `ea34b26c6e5f3babeb3eef61e5abb3da50f0f075` |
+| Upstream resolved SHA | `ea34b26c6e5f3babeb3eef61e5abb3da50f0f075` |
+| Mirror created | `2026-04-23T22:23:39Z` |
+| Description | Qwen3-4B Instruct 2507 OpenVINO INT4 corrector layout. |
+| License metadata | `{"license": "apache-2.0", "license_files": [], "license_tags": ["license:apache-2.0"]}` |
+## Installer Contract
+This mirror corresponds to `parakeet/installer/wrapper/model_catalog.py`.
+Required files for installer validation:
+```json
+[
+  "config.json",
+  "generation_config.json",
+  "chat_template.jinja",
+  "added_tokens.json",
+  "merges.txt",
+  "special_tokens_map.json",
+  "tokenizer.json",
+  "tokenizer_config.json",
+  "vocab.json",
+  "graph.pbtxt",
+  "openvino_model.xml",
+  "openvino_model.bin",
+  "openvino_tokenizer.xml",
+  "openvino_tokenizer.bin",
+  "openvino_detokenizer.xml",
+  "openvino_detokenizer.bin"
+]
+```
+Allowed installer subset patterns:
+```json
+[]
+```
+## Redistribution Note
+Do not make this repository public unless the upstream license and model card
+allow redistribution for the intended use. Private mirrors are for operational
+distribution convenience and reproducible installs.

added_tokens.json ADDED Viewed

	@@ -0,0 +1,28 @@

+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja ADDED Viewed

	@@ -0,0 +1,61 @@

+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function 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><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) 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 %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json ADDED Viewed

	@@ -0,0 +1,68 @@

+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 262144,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 5000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,13 @@

+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.53.0"
+}

graph.pbtxt ADDED Viewed

	@@ -0,0 +1,37 @@

+# File created with: OpenVINO Model Server 2025.4.0.8db21b81
+    input_stream: "HTTP_REQUEST_PAYLOAD:input"
+    output_stream: "HTTP_RESPONSE_PAYLOAD:output"
+    node: {
+    name: "LLMExecutor"
+    calculator: "HttpLLMCalculator"
+    input_stream: "LOOPBACK:loopback"
+    input_stream: "HTTP_REQUEST_PAYLOAD:input"
+    input_side_packet: "LLM_NODE_RESOURCES:llm"
+    output_stream: "LOOPBACK:loopback"
+    output_stream: "HTTP_RESPONSE_PAYLOAD:output"
+    input_stream_info: {
+        tag_index: 'LOOPBACK:0',
+        back_edge: true
+    }
+    node_options: {
+        [type.googleapis.com / mediapipe.LLMCalculatorOptions]: {
+            max_num_seqs:256,
+            device: "NPU",
+            models_path: "./",
+            plugin_config: '{"NPUW_LLM_ENABLE_PREFIX_CACHING":true}',
+            enable_prefix_caching: true,
+            cache_size: 2,
+        }
+    }
+    input_stream_handler {
+        input_stream_handler: "SyncSetInputStreamHandler",
+        options {
+        [mediapipe.SyncSetInputStreamHandlerOptions.ext] {
+            sync_set {
+            tag_index: "LOOPBACK:0"
+            }
+        }
+        }
+    }
+    }

merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

openvino_detokenizer.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d73093f72c80ebcaffb76a192727170ecd3c6a06c4df52df0e76b3f70ad9d7f7
+size 2189717

openvino_detokenizer.xml ADDED Viewed

	@@ -0,0 +1,220 @@

+<?xml version="1.0"?>
+<net name="detokenizer" version="11">
+	<layers>
+		<layer id="0" name="Parameter_122293" type="Parameter" version="opset1">
+			<data shape="?,?" element_type="i64" />
+			<output>
+				<port id="0" precision="I64" names="Parameter_122293">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1" name="Convert_122492" type="Convert" version="opset1">
+			<data destination_type="i32" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="2" name="Constant_122295" type="Const" version="opset1">
+			<data element_type="i32" shape="151669" offset="0" size="606676" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>151669</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="3" name="Constant_122297" type="Const" version="opset1">
+			<data element_type="i32" shape="151669" offset="606676" size="606676" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>151669</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="4" name="Constant_122299" type="Const" version="opset1">
+			<data element_type="u8" shape="976309" offset="1213352" size="976309" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>976309</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="5" name="Slice_122304" type="Const" version="opset1">
+			<data element_type="i32" shape="14" offset="2189661" size="56" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>14</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="6" name="VocabDecoder_122306" type="VocabDecoder" version="extension">
+			<data skip_tokens="" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>151669</dim>
+				</port>
+				<port id="2" precision="I32">
+					<dim>151669</dim>
+				</port>
+				<port id="3" precision="U8">
+					<dim>976309</dim>
+				</port>
+				<port id="4" precision="I32">
+					<dim>14</dim>
+				</port>
+			</input>
+			<output>
+				<port id="5" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="6" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="7" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="8" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="9" precision="U8">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="7" name="FuzeRagged_122307" type="FuzeRagged" version="extension">
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="3" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="4" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="5" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="8" name="UTF8Validate_122308" type="UTF8Validate" version="extension">
+			<data replace_mode="true" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="U8">
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="3" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="4" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="5" precision="U8">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="9" name="StringTensorPack_122309" type="StringTensorPack" version="opset15">
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="U8">
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="3" precision="STRING" names="Result_122310,string_output">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="10" name="Result_122310" type="Result" version="opset1" output_names="Result_122310,string_output">
+			<input>
+				<port id="0" precision="STRING">
+					<dim>-1</dim>
+				</port>
+			</input>
+		</layer>
+	</layers>
+	<edges>
+		<edge from-layer="0" from-port="0" to-layer="1" to-port="0" />
+		<edge from-layer="1" from-port="1" to-layer="6" to-port="0" />
+		<edge from-layer="2" from-port="0" to-layer="6" to-port="1" />
+		<edge from-layer="3" from-port="0" to-layer="6" to-port="2" />
+		<edge from-layer="4" from-port="0" to-layer="6" to-port="3" />
+		<edge from-layer="5" from-port="0" to-layer="6" to-port="4" />
+		<edge from-layer="6" from-port="5" to-layer="7" to-port="0" />
+		<edge from-layer="6" from-port="6" to-layer="7" to-port="1" />
+		<edge from-layer="6" from-port="7" to-layer="7" to-port="2" />
+		<edge from-layer="6" from-port="8" to-layer="7" to-port="3" />
+		<edge from-layer="6" from-port="9" to-layer="8" to-port="2" />
+		<edge from-layer="7" from-port="4" to-layer="8" to-port="0" />
+		<edge from-layer="7" from-port="5" to-layer="8" to-port="1" />
+		<edge from-layer="8" from-port="3" to-layer="9" to-port="0" />
+		<edge from-layer="8" from-port="4" to-layer="9" to-port="1" />
+		<edge from-layer="8" from-port="5" to-layer="9" to-port="2" />
+		<edge from-layer="9" from-port="3" to-layer="10" to-port="0" />
+	</edges>
+	<rt_info>
+		<add_attention_mask value="True" />
+		<add_prefix_space />
+		<add_special_tokens value="True" />
+		<chat_template value="{%- if tools %}&#10;    {{- '&lt;|im_start|>system\n' }}&#10;    {%- if messages[0].role == 'system' %}&#10;        {{- messages[0].content + '\n\n' }}&#10;    {%- endif %}&#10;    {{- &quot;# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within &lt;tools>&lt;/tools> XML tags:\n&lt;tools>&quot; }}&#10;    {%- for tool in tools %}&#10;        {{- &quot;\n&quot; }}&#10;        {{- tool | tojson }}&#10;    {%- endfor %}&#10;    {{- &quot;\n&lt;/tools>\n\nFor each function call, return a json object with function name and arguments within &lt;tool_call>&lt;/tool_call> XML tags:\n&lt;tool_call>\n{\&quot;name\&quot;: &lt;function-name>, \&quot;arguments\&quot;: &lt;args-json-object>}\n&lt;/tool_call>&lt;|im_end|>\n&quot; }}&#10;{%- else %}&#10;    {%- if messages[0].role == 'system' %}&#10;        {{- '&lt;|im_start|>system\n' + messages[0].content + '&lt;|im_end|>\n' }}&#10;    {%- endif %}&#10;{%- endif %}&#10;{%- for message in messages %}&#10;    {%- if message.content is string %}&#10;        {%- set content = message.content %}&#10;    {%- else %}&#10;        {%- set content = '' %}&#10;    {%- endif %}&#10;    {%- if (message.role == &quot;user&quot;) or (message.role == &quot;system&quot; and not loop.first) %}&#10;        {{- '&lt;|im_start|>' + message.role + '\n' + content + '&lt;|im_end|>' + '\n' }}&#10;    {%- elif message.role == &quot;assistant&quot; %}&#10;        {{- '&lt;|im_start|>' + message.role + '\n' + content }}&#10;        {%- if message.tool_calls %}&#10;            {%- for tool_call in message.tool_calls %}&#10;                {%- if (loop.first and content) or (not loop.first) %}&#10;                    {{- '\n' }}&#10;                {%- endif %}&#10;                {%- if tool_call.function %}&#10;                    {%- set tool_call = tool_call.function %}&#10;                {%- endif %}&#10;                {{- '&lt;tool_call>\n{&quot;name&quot;: &quot;' }}&#10;                {{- tool_call.name }}&#10;                {{- '&quot;, &quot;arguments&quot;: ' }}&#10;                {%- if tool_call.arguments is string %}&#10;                    {{- tool_call.arguments }}&#10;                {%- else %}&#10;                    {{- tool_call.arguments | tojson }}&#10;                {%- endif %}&#10;                {{- '}\n&lt;/tool_call>' }}&#10;            {%- endfor %}&#10;        {%- endif %}&#10;        {{- '&lt;|im_end|>\n' }}&#10;    {%- elif message.role == &quot;tool&quot; %}&#10;        {%- if loop.first or (messages[loop.index0 - 1].role != &quot;tool&quot;) %}&#10;            {{- '&lt;|im_start|>user' }}&#10;        {%- endif %}&#10;        {{- '\n&lt;tool_response>\n' }}&#10;        {{- content }}&#10;        {{- '\n&lt;/tool_response>' }}&#10;        {%- if loop.last or (messages[loop.index0 + 1].role != &quot;tool&quot;) %}&#10;            {{- '&lt;|im_end|>\n' }}&#10;        {%- endif %}&#10;    {%- endif %}&#10;{%- endfor %}&#10;{%- if add_generation_prompt %}&#10;    {{- '&lt;|im_start|>assistant\n' }}&#10;{%- endif %}" />
+		<clean_up_tokenization_spaces />
+		<detokenizer_input_type value="i64" />
+		<eos_token_id value="151645" />
+		<handle_special_tokens_with_re />
+		<max_length />
+		<number_of_inputs value="1" />
+		<openvino_tokenizers_version value="2026.0.0.0-632-47cea02a2d4" />
+		<openvino_version value="2026.0.0-20897-967e454238b" />
+		<original_post_processor_template value="{&quot;type&quot;: &quot;ByteLevel&quot;, &quot;add_prefix_space&quot;: false, &quot;trim_offsets&quot;: false, &quot;use_regex&quot;: false}" />
+		<original_tokenizer_class value="&lt;class 'transformers.models.qwen2.tokenization_qwen2_fast.Qwen2TokenizerFast'>" />
+		<pad_token_id value="151643" />
+		<processed_post_processor_template value="{&quot;single&quot;: {&quot;ids&quot;: [-1], &quot;type_ids&quot;: [0]}, &quot;pair&quot;: {&quot;ids&quot;: [-1, -2], &quot;type_ids&quot;: [0, 0]}}" />
+		<sentencepiece_version value="0.2.1" />
+		<skip_special_tokens value="True" />
+		<streaming_detokenizer value="False" />
+		<tokenizer_output_type value="i64" />
+		<tokenizers_version value="0.21.4" />
+		<transformers_version value="4.53.0" />
+		<use_max_padding value="False" />
+		<use_sentencepiece_backend value="False" />
+		<utf8_replace_mode value="replace" />
+		<with_detokenizer value="True" />
+	</rt_info>
+</net>

openvino_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8da075877b5b18ca3a612af322e6dc19b761f0c2aef2907d4c1781acc0609355
+size 2263625405

openvino_model.xml ADDED Viewed

The diff for this file is too large to render. See raw diff

openvino_tokenizer.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:42c707b40104b8416a2e106eaa4989effa50bfec80753b412af3a1cb52b9460d
+size 5588831

openvino_tokenizer.xml ADDED Viewed

	@@ -0,0 +1,771 @@

+<?xml version="1.0"?>
+<net name="tokenizer" version="11">
+	<layers>
+		<layer id="0" name="Parameter_122165" type="Parameter" version="opset1">
+			<data shape="?" element_type="string" />
+			<output>
+				<port id="0" precision="STRING" names="Parameter_122165">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="1" name="Constant_122171" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="0" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="2" name="StringTensorUnpack_122166" type="StringTensorUnpack" version="opset15">
+			<input>
+				<port id="0" precision="STRING">
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="3" precision="U8">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="3" name="ShapeOf_122167" type="ShapeOf" version="opset3">
+			<data output_type="i64" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I64">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="4" name="Constant_122168" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="0" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="5" name="Constant_122169" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="0" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="6" name="Gather_122170" type="Gather" version="opset8">
+			<data batch_dims="0" />
+			<input>
+				<port id="0" precision="I64">
+					<dim>1</dim>
+				</port>
+				<port id="1" precision="I32" />
+				<port id="2" precision="I32" />
+			</input>
+			<output>
+				<port id="3" precision="I64" />
+			</output>
+		</layer>
+		<layer id="7" name="Constant_122172" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="4" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="8" name="Range_122173" type="Range" version="opset4">
+			<data output_type="i32" />
+			<input>
+				<port id="0" precision="I32" />
+				<port id="1" precision="I64" />
+				<port id="2" precision="I32" />
+			</input>
+			<output>
+				<port id="3" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="9" name="Constant_122174" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="4" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="10" name="Constant_122175" type="Const" version="opset1">
+			<data element_type="i64" shape="" offset="8" size="8" />
+			<output>
+				<port id="0" precision="I64" />
+			</output>
+		</layer>
+		<layer id="11" name="Add_122176" type="Add" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="I64" />
+				<port id="1" precision="I64" />
+			</input>
+			<output>
+				<port id="2" precision="I64" />
+			</output>
+		</layer>
+		<layer id="12" name="Constant_122177" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="4" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="13" name="Range_122178" type="Range" version="opset4">
+			<data output_type="i32" />
+			<input>
+				<port id="0" precision="I32" />
+				<port id="1" precision="I64" />
+				<port id="2" precision="I32" />
+			</input>
+			<output>
+				<port id="3" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="14" name="Constant_122242" type="Const" version="opset1">
+			<data element_type="u8" shape="462" offset="16" size="462" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>462</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="15" name="SpecialTokensSplit_122243" type="SpecialTokensSplit" version="extension">
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="3" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="4" precision="U8">
+					<dim>-1</dim>
+				</port>
+				<port id="5" precision="U8">
+					<dim>462</dim>
+				</port>
+			</input>
+			<output>
+				<port id="6" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="7" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="8" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="9" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="10" precision="U8">
+					<dim>-1</dim>
+				</port>
+				<port id="11" precision="BOOL">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="16" name="CharsMapNormalization_122244" type="CharsMapNormalization" version="extension">
+			<data add_dummy_prefix="false" remove_extra_whitespaces="false" escape_whitespaces="false" normalization_form="nfc" case_fold="false" nmt="false" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="U8">
+					<dim>-1</dim>
+				</port>
+				<port id="3" precision="BOOL">
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="4" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="5" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="6" precision="U8">
+					<dim>-1</dim>
+				</port>
+				<port id="7" precision="BOOL">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="17" name="Constant_122246" type="Const" version="opset1">
+			<data element_type="u8" shape="110" offset="478" size="110" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>110</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="18" name="RegexSplit_122247" type="RegexSplit" version="extension">
+			<data behaviour="isolate" invert="false" max_splits="-1" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="3" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="4" precision="U8">
+					<dim>-1</dim>
+				</port>
+				<port id="5" precision="BOOL">
+					<dim>-1</dim>
+				</port>
+				<port id="6" precision="U8">
+					<dim>110</dim>
+				</port>
+			</input>
+			<output>
+				<port id="7" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="8" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="9" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="10" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="11" precision="U8">
+					<dim>-1</dim>
+				</port>
+				<port id="12" precision="BOOL">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="19" name="Constant_122249" type="Const" version="opset1">
+			<data element_type="i32" shape="151669" offset="588" size="606676" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>151669</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="20" name="Constant_122251" type="Const" version="opset1">
+			<data element_type="i32" shape="151669" offset="607264" size="606676" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>151669</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="21" name="Constant_122253" type="Const" version="opset1">
+			<data element_type="u8" shape="976309" offset="1213940" size="976309" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>976309</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="22" name="Constant_122261" type="Const" version="opset1">
+			<data element_type="i32" shape="151387" offset="2190249" size="605548" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>151387</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="23" name="Constant_122263" type="Const" version="opset1">
+			<data element_type="i32" shape="151387" offset="2795797" size="605548" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>151387</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="24" name="Constant_122265" type="Const" version="opset1">
+			<data element_type="u8" shape="491359" offset="3401345" size="491359" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>491359</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="25" name="Constant_122267" type="Const" version="opset1">
+			<data element_type="i32" shape="151387" offset="3892704" size="605548" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>151387</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="26" name="Constant_122269" type="Const" version="opset1">
+			<data element_type="i32" shape="151387" offset="4498252" size="605548" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>151387</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="27" name="Constant_122271" type="Const" version="opset1">
+			<data element_type="u8" shape="484354" offset="5103800" size="484354" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>484354</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="28" name="Constant_122255" type="Const" version="opset1">
+			<data element_type="i32" shape="26" offset="5588154" size="104" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>26</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="29" name="Constant_122257" type="Const" version="opset1">
+			<data element_type="i32" shape="26" offset="5588258" size="104" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>26</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="30" name="Constant_122259" type="Const" version="opset1">
+			<data element_type="u8" shape="340" offset="5588362" size="340" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>340</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="31" name="Constant_122272" type="Const" version="opset1">
+			<data element_type="i32" shape="26" offset="5588702" size="104" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>26</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="32" name="BPETokenizer_122273" type="BPETokenizer" version="extension">
+			<data unk_token="" fuse_unk="false" suffix_indicator="" end_suffix="" byte_fallback="false" cache_capacity="30328" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="3" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="4" precision="U8">
+					<dim>-1</dim>
+				</port>
+				<port id="5" precision="I32">
+					<dim>151669</dim>
+				</port>
+				<port id="6" precision="I32">
+					<dim>151669</dim>
+				</port>
+				<port id="7" precision="U8">
+					<dim>976309</dim>
+				</port>
+				<port id="8" precision="I32">
+					<dim>151387</dim>
+				</port>
+				<port id="9" precision="I32">
+					<dim>151387</dim>
+				</port>
+				<port id="10" precision="U8">
+					<dim>491359</dim>
+				</port>
+				<port id="11" precision="I32">
+					<dim>151387</dim>
+				</port>
+				<port id="12" precision="I32">
+					<dim>151387</dim>
+				</port>
+				<port id="13" precision="U8">
+					<dim>484354</dim>
+				</port>
+				<port id="14" precision="I32">
+					<dim>26</dim>
+				</port>
+				<port id="15" precision="I32">
+					<dim>26</dim>
+				</port>
+				<port id="16" precision="U8">
+					<dim>340</dim>
+				</port>
+				<port id="17" precision="I32">
+					<dim>26</dim>
+				</port>
+			</input>
+			<output>
+				<port id="18" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="19" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="20" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="33" name="Constant_122274" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="5588806" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="34" name="Constant_122276" type="Const" version="opset1">
+			<data element_type="u8" shape="4" offset="5588810" size="4" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>4</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="35" name="Constant_122278" type="Const" version="opset1">
+			<data element_type="u8" shape="13" offset="5588814" size="13" />
+			<output>
+				<port id="0" precision="U8">
+					<dim>13</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="36" name="Truncate_122279" type="Truncate" version="extension">
+			<data m_num_inputs="1" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="3" precision="I32" />
+				<port id="4" precision="U8">
+					<dim>4</dim>
+				</port>
+				<port id="5" precision="U8">
+					<dim>13</dim>
+				</port>
+			</input>
+			<output>
+				<port id="6" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="7" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="8" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="37" name="Constant_122280" type="Const" version="opset1">
+			<data element_type="i32" shape="1" offset="0" size="4" />
+			<output>
+				<port id="0" precision="I32">
+					<dim>1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="38" name="CombineSegments_122281" type="CombineSegments" version="extension">
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="3" precision="I32">
+					<dim>1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="4" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="5" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="6" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="7" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="8" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="9" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="39" name="Subtract_122282" type="Subtract" version="opset1">
+			<data auto_broadcast="numpy" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="40" name="Constant_122283" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="0" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="41" name="ReduceMax_122284" type="ReduceMax" version="opset1">
+			<data keep_dims="false" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32" />
+			</input>
+			<output>
+				<port id="2" precision="I32" />
+			</output>
+		</layer>
+		<layer id="42" name="Constant_122285" type="Const" version="opset1">
+			<data element_type="i32" shape="" offset="5588827" size="4" />
+			<output>
+				<port id="0" precision="I32" />
+			</output>
+		</layer>
+		<layer id="43" name="RaggedToDense_122286" type="RaggedToDense" version="extension">
+			<data pad_right="false" m_pad_max_length="false" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="2" precision="I32">
+					<dim>-1</dim>
+				</port>
+				<port id="3" precision="I32" />
+				<port id="4" precision="I32" />
+			</input>
+			<output>
+				<port id="5" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+				<port id="6" precision="BOOL">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="44" name="Convert_122287" type="Convert" version="opset1">
+			<data destination_type="i32" />
+			<input>
+				<port id="0" precision="BOOL">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="45" name="Convert_122287.0" type="Convert" version="opset1">
+			<data destination_type="i64" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I64" names="attention_mask">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="46" name="RaggedToDense_122286.0" type="Convert" version="opset1">
+			<data destination_type="i64" />
+			<input>
+				<port id="0" precision="I32">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+			<output>
+				<port id="1" precision="I64" names="input_ids">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</output>
+		</layer>
+		<layer id="47" name="Result_122290" type="Result" version="opset1" output_names="input_ids">
+			<input>
+				<port id="0" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+		</layer>
+		<layer id="48" name="Result_122292" type="Result" version="opset1" output_names="attention_mask">
+			<input>
+				<port id="0" precision="I64">
+					<dim>-1</dim>
+					<dim>-1</dim>
+				</port>
+			</input>
+		</layer>
+	</layers>
+	<edges>
+		<edge from-layer="0" from-port="0" to-layer="2" to-port="0" />
+		<edge from-layer="1" from-port="0" to-layer="8" to-port="0" />
+		<edge from-layer="2" from-port="1" to-layer="3" to-port="0" />
+		<edge from-layer="2" from-port="1" to-layer="15" to-port="2" />
+		<edge from-layer="2" from-port="2" to-layer="15" to-port="3" />
+		<edge from-layer="2" from-port="3" to-layer="15" to-port="4" />
+		<edge from-layer="3" from-port="1" to-layer="6" to-port="0" />
+		<edge from-layer="4" from-port="0" to-layer="6" to-port="1" />
+		<edge from-layer="5" from-port="0" to-layer="6" to-port="2" />
+		<edge from-layer="6" from-port="3" to-layer="8" to-port="1" />
+		<edge from-layer="6" from-port="3" to-layer="11" to-port="0" />
+		<edge from-layer="7" from-port="0" to-layer="8" to-port="2" />
+		<edge from-layer="8" from-port="3" to-layer="15" to-port="0" />
+		<edge from-layer="9" from-port="0" to-layer="13" to-port="0" />
+		<edge from-layer="10" from-port="0" to-layer="11" to-port="1" />
+		<edge from-layer="11" from-port="2" to-layer="13" to-port="1" />
+		<edge from-layer="12" from-port="0" to-layer="13" to-port="2" />
+		<edge from-layer="13" from-port="3" to-layer="15" to-port="1" />
+		<edge from-layer="14" from-port="0" to-layer="15" to-port="5" />
+		<edge from-layer="15" from-port="8" to-layer="16" to-port="0" />
+		<edge from-layer="15" from-port="9" to-layer="16" to-port="1" />
+		<edge from-layer="15" from-port="10" to-layer="16" to-port="2" />
+		<edge from-layer="15" from-port="11" to-layer="16" to-port="3" />
+		<edge from-layer="15" from-port="6" to-layer="18" to-port="0" />
+		<edge from-layer="15" from-port="7" to-layer="18" to-port="1" />
+		<edge from-layer="16" from-port="4" to-layer="18" to-port="2" />
+		<edge from-layer="16" from-port="5" to-layer="18" to-port="3" />
+		<edge from-layer="16" from-port="6" to-layer="18" to-port="4" />
+		<edge from-layer="16" from-port="7" to-layer="18" to-port="5" />
+		<edge from-layer="17" from-port="0" to-layer="18" to-port="6" />
+		<edge from-layer="18" from-port="7" to-layer="32" to-port="0" />
+		<edge from-layer="18" from-port="8" to-layer="32" to-port="1" />
+		<edge from-layer="18" from-port="9" to-layer="32" to-port="2" />
+		<edge from-layer="18" from-port="10" to-layer="32" to-port="3" />
+		<edge from-layer="18" from-port="11" to-layer="32" to-port="4" />
+		<edge from-layer="19" from-port="0" to-layer="32" to-port="5" />
+		<edge from-layer="20" from-port="0" to-layer="32" to-port="6" />
+		<edge from-layer="21" from-port="0" to-layer="32" to-port="7" />
+		<edge from-layer="22" from-port="0" to-layer="32" to-port="8" />
+		<edge from-layer="23" from-port="0" to-layer="32" to-port="9" />
+		<edge from-layer="24" from-port="0" to-layer="32" to-port="10" />
+		<edge from-layer="25" from-port="0" to-layer="32" to-port="11" />
+		<edge from-layer="26" from-port="0" to-layer="32" to-port="12" />
+		<edge from-layer="27" from-port="0" to-layer="32" to-port="13" />
+		<edge from-layer="28" from-port="0" to-layer="32" to-port="14" />
+		<edge from-layer="29" from-port="0" to-layer="32" to-port="15" />
+		<edge from-layer="30" from-port="0" to-layer="32" to-port="16" />
+		<edge from-layer="31" from-port="0" to-layer="32" to-port="17" />
+		<edge from-layer="32" from-port="18" to-layer="36" to-port="0" />
+		<edge from-layer="32" from-port="19" to-layer="36" to-port="1" />
+		<edge from-layer="32" from-port="20" to-layer="36" to-port="2" />
+		<edge from-layer="33" from-port="0" to-layer="36" to-port="3" />
+		<edge from-layer="34" from-port="0" to-layer="36" to-port="4" />
+		<edge from-layer="35" from-port="0" to-layer="36" to-port="5" />
+		<edge from-layer="36" from-port="6" to-layer="38" to-port="0" />
+		<edge from-layer="36" from-port="7" to-layer="38" to-port="1" />
+		<edge from-layer="36" from-port="8" to-layer="38" to-port="2" />
+		<edge from-layer="37" from-port="0" to-layer="38" to-port="3" />
+		<edge from-layer="38" from-port="5" to-layer="39" to-port="0" />
+		<edge from-layer="38" from-port="4" to-layer="39" to-port="1" />
+		<edge from-layer="38" from-port="4" to-layer="43" to-port="0" />
+		<edge from-layer="38" from-port="5" to-layer="43" to-port="1" />
+		<edge from-layer="38" from-port="6" to-layer="43" to-port="2" />
+		<edge from-layer="39" from-port="2" to-layer="41" to-port="0" />
+		<edge from-layer="40" from-port="0" to-layer="41" to-port="1" />
+		<edge from-layer="41" from-port="2" to-layer="43" to-port="3" />
+		<edge from-layer="42" from-port="0" to-layer="43" to-port="4" />
+		<edge from-layer="43" from-port="6" to-layer="44" to-port="0" />
+		<edge from-layer="43" from-port="5" to-layer="46" to-port="0" />
+		<edge from-layer="44" from-port="1" to-layer="45" to-port="0" />
+		<edge from-layer="45" from-port="1" to-layer="48" to-port="0" />
+		<edge from-layer="46" from-port="1" to-layer="47" to-port="0" />
+	</edges>
+	<rt_info>
+		<add_attention_mask value="True" />
+		<add_prefix_space />
+		<add_special_tokens value="True" />
+		<chat_template value="{%- if tools %}&#10;    {{- '&lt;|im_start|>system\n' }}&#10;    {%- if messages[0].role == 'system' %}&#10;        {{- messages[0].content + '\n\n' }}&#10;    {%- endif %}&#10;    {{- &quot;# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within &lt;tools>&lt;/tools> XML tags:\n&lt;tools>&quot; }}&#10;    {%- for tool in tools %}&#10;        {{- &quot;\n&quot; }}&#10;        {{- tool | tojson }}&#10;    {%- endfor %}&#10;    {{- &quot;\n&lt;/tools>\n\nFor each function call, return a json object with function name and arguments within &lt;tool_call>&lt;/tool_call> XML tags:\n&lt;tool_call>\n{\&quot;name\&quot;: &lt;function-name>, \&quot;arguments\&quot;: &lt;args-json-object>}\n&lt;/tool_call>&lt;|im_end|>\n&quot; }}&#10;{%- else %}&#10;    {%- if messages[0].role == 'system' %}&#10;        {{- '&lt;|im_start|>system\n' + messages[0].content + '&lt;|im_end|>\n' }}&#10;    {%- endif %}&#10;{%- endif %}&#10;{%- for message in messages %}&#10;    {%- if message.content is string %}&#10;        {%- set content = message.content %}&#10;    {%- else %}&#10;        {%- set content = '' %}&#10;    {%- endif %}&#10;    {%- if (message.role == &quot;user&quot;) or (message.role == &quot;system&quot; and not loop.first) %}&#10;        {{- '&lt;|im_start|>' + message.role + '\n' + content + '&lt;|im_end|>' + '\n' }}&#10;    {%- elif message.role == &quot;assistant&quot; %}&#10;        {{- '&lt;|im_start|>' + message.role + '\n' + content }}&#10;        {%- if message.tool_calls %}&#10;            {%- for tool_call in message.tool_calls %}&#10;                {%- if (loop.first and content) or (not loop.first) %}&#10;                    {{- '\n' }}&#10;                {%- endif %}&#10;                {%- if tool_call.function %}&#10;                    {%- set tool_call = tool_call.function %}&#10;                {%- endif %}&#10;                {{- '&lt;tool_call>\n{&quot;name&quot;: &quot;' }}&#10;                {{- tool_call.name }}&#10;                {{- '&quot;, &quot;arguments&quot;: ' }}&#10;                {%- if tool_call.arguments is string %}&#10;                    {{- tool_call.arguments }}&#10;                {%- else %}&#10;                    {{- tool_call.arguments | tojson }}&#10;                {%- endif %}&#10;                {{- '}\n&lt;/tool_call>' }}&#10;            {%- endfor %}&#10;        {%- endif %}&#10;        {{- '&lt;|im_end|>\n' }}&#10;    {%- elif message.role == &quot;tool&quot; %}&#10;        {%- if loop.first or (messages[loop.index0 - 1].role != &quot;tool&quot;) %}&#10;            {{- '&lt;|im_start|>user' }}&#10;        {%- endif %}&#10;        {{- '\n&lt;tool_response>\n' }}&#10;        {{- content }}&#10;        {{- '\n&lt;/tool_response>' }}&#10;        {%- if loop.last or (messages[loop.index0 + 1].role != &quot;tool&quot;) %}&#10;            {{- '&lt;|im_end|>\n' }}&#10;        {%- endif %}&#10;    {%- endif %}&#10;{%- endfor %}&#10;{%- if add_generation_prompt %}&#10;    {{- '&lt;|im_start|>assistant\n' }}&#10;{%- endif %}" />
+		<clean_up_tokenization_spaces />
+		<detokenizer_input_type value="i64" />
+		<eos_token_id value="151645" />
+		<handle_special_tokens_with_re />
+		<max_length />
+		<number_of_inputs value="1" />
+		<openvino_tokenizers_version value="2026.0.0.0-632-47cea02a2d4" />
+		<openvino_version value="2026.0.0-20897-967e454238b" />
+		<original_post_processor_template value="{&quot;type&quot;: &quot;ByteLevel&quot;, &quot;add_prefix_space&quot;: false, &quot;trim_offsets&quot;: false, &quot;use_regex&quot;: false}" />
+		<original_tokenizer_class value="&lt;class 'transformers.models.qwen2.tokenization_qwen2_fast.Qwen2TokenizerFast'>" />
+		<pad_token_id value="151643" />
+		<processed_post_processor_template value="{&quot;single&quot;: {&quot;ids&quot;: [-1], &quot;type_ids&quot;: [0]}, &quot;pair&quot;: {&quot;ids&quot;: [-1, -2], &quot;type_ids&quot;: [0, 0]}}" />
+		<sentencepiece_version value="0.2.1" />
+		<skip_special_tokens value="True" />
+		<streaming_detokenizer value="False" />
+		<tokenizer_output_type value="i64" />
+		<tokenizers_version value="0.21.4" />
+		<transformers_version value="4.53.0" />
+		<use_max_padding value="False" />
+		<use_sentencepiece_backend value="False" />
+		<utf8_replace_mode value="replace" />
+		<with_detokenizer value="True" />
+	</rt_info>
+</net>

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,31 @@

+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,239 @@

+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1010000,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff

voicescribe-model-layout.json ADDED Viewed

	@@ -0,0 +1,36 @@

+{
+  "schema_version": 1,
+  "generated_at": "2026-04-23T22:23:39Z",
+  "layout_key": "corrector",
+  "target_dir": "qwen3-4b-instruct-2507-ov",
+  "upstream_repo": "anubhav200/Qwen3-4B-Instruct-2507-openvino-int4",
+  "upstream_revision": "ea34b26c6e5f3babeb3eef61e5abb3da50f0f075",
+  "upstream_sha": "ea34b26c6e5f3babeb3eef61e5abb3da50f0f075",
+  "description": "Qwen3-4B Instruct 2507 OpenVINO INT4 corrector layout.",
+  "required_files": [
+    "config.json",
+    "generation_config.json",
+    "chat_template.jinja",
+    "added_tokens.json",
+    "merges.txt",
+    "special_tokens_map.json",
+    "tokenizer.json",
+    "tokenizer_config.json",
+    "vocab.json",
+    "graph.pbtxt",
+    "openvino_model.xml",
+    "openvino_model.bin",
+    "openvino_tokenizer.xml",
+    "openvino_tokenizer.bin",
+    "openvino_detokenizer.xml",
+    "openvino_detokenizer.bin"
+  ],
+  "allow_patterns": [],
+  "license_metadata": {
+    "license": "apache-2.0",
+    "license_tags": [
+      "license:apache-2.0"
+    ],
+    "license_files": []
+  }
+}