Upload LoRA adapter v3

README.md

@@ -1,72 +1,46 @@
 ---
 base_model: Qwen/Qwen3-4B-Instruct-2507
 datasets:
-- u-10bei/sft_alfworld_trajectory_dataset
-- u-10bei/sft_alfworld_trajectory_dataset_v2
-- u-10bei/sft_alfworld_trajectory_dataset_v3
-- u-10bei/sft_alfworld_trajectory_dataset_v5
-- u-10bei/dbbench_sft_dataset_react_v4
+- u-10bei/structured_data_with_cot_dataset
 language:
 - en
 license: apache-2.0
 library_name: peft
 pipeline_tag: text-generation
 tags:
+- qlora
 - lora
-- agent
-- tool-use
-- alfworld
-- dbbench
+- structured-output
 ---
 
-# Qwen3-4B ALFWorld+DBBench Mixed LoRA Adapter (r=64)
+＜clean version 3＞
 
 This repository provides a **LoRA adapter** fine-tuned from
-**Qwen/Qwen3-4B-Instruct-2507** using **LoRA + Unsloth**.
+**Qwen/Qwen3-4B-Instruct-2507** using **QLoRA (4-bit, Unsloth)**.
 
 This repository contains **LoRA adapter weights only**.
 The base model must be loaded separately.
 
 ## Training Objective
 
-This adapter is trained to improve **multi-turn agent task performance**
-on ALFWorld (household tasks) and DBBench (database operations).
+This adapter is trained to improve **structured output accuracy**
+(JSON / YAML / XML / TOML / CSV).
 
-Loss is applied to **all assistant turns** in the multi-turn trajectory,
-enabling the model to learn environment observation, action selection,
-tool use, and recovery from errors.
+Loss is applied only to the final assistant output,
+while intermediate reasoning (Chain-of-Thought) is masked.
 
 ## Training Configuration
 
 - Base model: Qwen/Qwen3-4B-Instruct-2507
-- Method: LoRA (full precision base)
+- Method: QLoRA (4-bit)
 - Max sequence length: 2048
 - Epochs: 3
-- Learning rate: 2e-04
+- Learning rate: 2e-06
 - LoRA: r=64, alpha=128
 
-## Usage
-
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
-from peft import PeftModel
-import torch
-
-base = "Qwen/Qwen3-4B-Instruct-2507"
-adapter = "your_id/your-repo"
-
-tokenizer = AutoTokenizer.from_pretrained(base)
-model = AutoModelForCausalLM.from_pretrained(
-    base,
-    torch_dtype=torch.float16,
-    device_map="auto",
-)
-model = PeftModel.from_pretrained(model, adapter)
-```
-
 ## Sources & Terms (IMPORTANT)
 
-Training data: u-10bei/sft_alfworld_trajectory_dataset_v5 + u-10bei/dbbench_sft_dataset_react_v4
+Training data: u-10bei/structured_data_with_cot_dataset
 
-Dataset License: MIT License. This dataset is used and distributed under the terms of the MIT License.
-Compliance: Users must comply with the MIT license (including copyright notice) and the base model's original terms of use.
+Dataset License: MIT License.
+Compliance: Users must comply with the MIT license and the base model's original terms of use.

adapter_config.json

@@ -1,12 +1,18 @@
 {
+  "alora_invocation_tokens": null,
   "alpha_pattern": {},
+  "arrow_config": null,
   "auto_mapping": {
     "base_model_class": "Qwen3ForCausalLM",
     "parent_library": "transformers.models.qwen3.modeling_qwen3",
     "unsloth_fixed": true
   },
-  "base_model_name_or_path": "unsloth/Qwen3-4B-Instruct-2507",
+  "base_model_name_or_path": "unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit",
   "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -15,24 +21,30 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 128,
-  "lora_dropout": 0.0,
+  "lora_bias": false,
+  "lora_dropout": 0.04,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
   "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
+    "q_proj",
     "k_proj",
+    "gate_proj",
+    "o_proj",
     "up_proj",
     "down_proj",
-    "o_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
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da2e40b92d02b9398ad80b68d3c3c85f8f9fce96dfd3baf909c4b75e98bf4174
+oid sha256:41548c2466e91a4d418f5c3e23726adb53510fa1ab23fcb14d019e05e95e16a6
 size 528550256

tokenizer_config.json

@@ -233,7 +233,7 @@
   "extra_special_tokens": {},
   "model_max_length": 262144,
   "pad_token": "<|vision_pad|>",
-  "padding_side": "left",
+  "padding_side": "right",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null