Upload LoRA adapter (README written by author)

.gitattributes

@@ -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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,72 @@
+---
+base_model: unsloth/Qwen3-4B-Instruct-2507
+datasets:
+  - u-10bei/structured_data_with_cot_dataset_512_v5
+  - daichira/structured-5k-mix-sft
+  - daichira/structured-hard-sft-4k
+language:
+- en
+license: apache-2.0
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- qlora
+- lora
+- structured-output
+---
+
+unsloth_qwen3-4b-structured-output-lora-unsloth-17
+
+This repository provides a **LoRA adapter** fine-tuned from
+**unsloth/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 **structured output accuracy**
+(JSON / YAML / XML / TOML / CSV).
+
+Loss is applied only to the final assistant output,
+while intermediate reasoning (Chain-of-Thought) is masked.
+
+## Training Configuration
+
+- Base model: unsloth/Qwen3-4B-Instruct-2507
+- Method: QLoRA (4-bit)
+- Max sequence length: 2048
+- Epochs: 2
+- Learning rate: 1e-04
+- LoRA: r=128, alpha=256
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+import torch
+
+base = "unsloth/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/structured_data_with_cot_dataset_512_v5
+  - daichira/structured-5k-mix-sft
+  - daichira/structured-hard-sft-4k
+
+Dataset License: MIT License and CC BY 4.0.
+
+u-10bei/structured_data_with_cot_dataset_512_v2 is licensed under the MIT License.
+
+daichira/structured-5k-mix-sft and daichira/structured-hard-sft-4k is licensed under the CC BY 4.0 License.

adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "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-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,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8399816c6586ef1d7c9048095ae02482b9223b968c3ad5adaec994b1744962fe
+size 1057033224

added_tokens.json

@@ -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
+}

special_tokens_map.json

@@ -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": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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": 262144,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,163 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.4872591671845867,
+  "eval_steps": 50,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09944064636420137,
+      "grad_norm": 0.46565961837768555,
+      "learning_rate": 4.2857142857142856e-05,
+      "loss": 0.6606,
+      "step": 10
+    },
+    {
+      "epoch": 0.19888129272840274,
+      "grad_norm": 0.21156033873558044,
+      "learning_rate": 9.047619047619048e-05,
+      "loss": 0.2999,
+      "step": 20
+    },
+    {
+      "epoch": 0.2983219390926041,
+      "grad_norm": 0.12329144775867462,
+      "learning_rate": 9.951875672379424e-05,
+      "loss": 0.1788,
+      "step": 30
+    },
+    {
+      "epoch": 0.3977625854568055,
+      "grad_norm": 0.09375570714473724,
+      "learning_rate": 9.75795720043301e-05,
+      "loss": 0.1436,
+      "step": 40
+    },
+    {
+      "epoch": 0.49720323182100684,
+      "grad_norm": 0.07597427070140839,
+      "learning_rate": 9.421059630216991e-05,
+      "loss": 0.1316,
+      "step": 50
+    },
+    {
+      "epoch": 0.49720323182100684,
+      "eval_loss": 0.16200877726078033,
+      "eval_runtime": 148.7627,
+      "eval_samples_per_second": 4.551,
+      "eval_steps_per_second": 0.571,
+      "step": 50
+    },
+    {
+      "epoch": 0.5966438781852083,
+      "grad_norm": 0.12265671044588089,
+      "learning_rate": 8.951306909629492e-05,
+      "loss": 0.1238,
+      "step": 60
+    },
+    {
+      "epoch": 0.6960845245494096,
+      "grad_norm": 0.08245938271284103,
+      "learning_rate": 8.36281535320844e-05,
+      "loss": 0.1213,
+      "step": 70
+    },
+    {
+      "epoch": 0.795525170913611,
+      "grad_norm": 0.0956747829914093,
+      "learning_rate": 7.67326943950877e-05,
+      "loss": 0.1002,
+      "step": 80
+    },
+    {
+      "epoch": 0.8949658172778123,
+      "grad_norm": 0.08027094602584839,
+      "learning_rate": 6.903390383287794e-05,
+      "loss": 0.1032,
+      "step": 90
+    },
+    {
+      "epoch": 0.9944064636420137,
+      "grad_norm": 0.0625375509262085,
+      "learning_rate": 6.076313452182033e-05,
+      "loss": 0.0995,
+      "step": 100
+    },
+    {
+      "epoch": 0.9944064636420137,
+      "eval_loss": 0.13908806443214417,
+      "eval_runtime": 148.5524,
+      "eval_samples_per_second": 4.557,
+      "eval_steps_per_second": 0.572,
+      "step": 100
+    },
+    {
+      "epoch": 1.0894965817277813,
+      "grad_norm": 0.07910885661840439,
+      "learning_rate": 5.216892739834519e-05,
+      "loss": 0.1,
+      "step": 110
+    },
+    {
+      "epoch": 1.1889372280919825,
+      "grad_norm": 0.056128814816474915,
+      "learning_rate": 4.3509542874030986e-05,
+      "loss": 0.102,
+      "step": 120
+    },
+    {
+      "epoch": 1.288377874456184,
+      "grad_norm": 0.06342772394418716,
+      "learning_rate": 3.504519997538422e-05,
+      "loss": 0.0927,
+      "step": 130
+    },
+    {
+      "epoch": 1.3878185208203853,
+      "grad_norm": 0.08915788680315018,
+      "learning_rate": 2.703025662621793e-05,
+      "loss": 0.1011,
+      "step": 140
+    },
+    {
+      "epoch": 1.4872591671845867,
+      "grad_norm": 0.0749816745519638,
+      "learning_rate": 1.9705566059226448e-05,
+      "loss": 0.1062,
+      "step": 150
+    },
+    {
+      "epoch": 1.4872591671845867,
+      "eval_loss": 0.13421669602394104,
+      "eval_runtime": 148.5801,
+      "eval_samples_per_second": 4.556,
+      "eval_steps_per_second": 0.572,
+      "step": 150
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 202,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.319488295485522e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}