Upload phase2a-test-1k model - 2025-11-18 09:24:35

.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 +1,184 @@
+---
+license: apache-2.0
+base_model: unsloth/Qwen3-30B-A3B-Instruct-2507
+tags:
+- kaidol
+- roleplay
+- korean
+- qwen3
+- lora
+- unsloth
+language:
+- ko
+- en
+pipeline_tag: text-generation
+---
+
+# KAIDOL LLM Fine-tuning - PHASE2A-TEST-1K
+
+Korean AI Idol Roleplay Language Model based on unsloth/Qwen3-30B-A3B-Instruct-2507
+
+## Model Description
+
+이 모델은 K-pop 아이돌 스타일의 롤플레잉 및 공감 대화를 위해 fine-tuning된 LoRA adapter입니다.
+
+- **Base Model**: unsloth/Qwen3-30B-A3B-Instruct-2507
+- **Training Phase**: phase2a-test-1k
+- **Training Framework**: Unsloth 2025.11.3
+- **LoRA Rank**: 16
+- **LoRA Alpha**: 16
+- **Training Samples**: 1000
+
+## Training Configuration
+
+```json
+{
+  "model": "Qwen3-30B-A3B-Instruct-2507",
+  "phase": "phase2a-test-1k",
+  "dataset": "phase2-rp-base-1k",
+  "num_samples": 1000,
+  "lora_rank": 16,
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "learning_rate": 0.0002,
+  "batch_size": 2,
+  "gradient_accumulation_steps": 4,
+  "effective_batch_size": 32,
+  "max_steps": 100,
+  "warmup_steps": 10,
+  "max_seq_length": 2048,
+  "optimizer": "adamw_8bit",
+  "weight_decay": 0.01,
+  "lr_scheduler_type": "linear",
+  "precision": "bfloat16",
+  "device_map": "auto",
+  "gpus": "4x RTX 5090",
+  "training_time": "40 minutes",
+  "framework": "Unsloth 2025.11.3",
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj"
+  ]
+}
+```
+
+## Evaluation Metrics
+
+```json
+{
+  "training_loss": {
+    "initial": 2.3745,
+    "final": 1.5027,
+    "reduction_percent": 36.7
+  },
+  "training_metrics": {
+    "total_steps": 100,
+    "total_samples": 1000,
+    "training_time_seconds": 2380.49,
+    "training_time_minutes": 39.67,
+    "samples_per_second": 0.336,
+    "final_grad_norm": 0.1539,
+    "final_learning_rate": 0.0
+  },
+  "loss_progression": {
+    "step_5": 2.3745,
+    "step_10": 1.531,
+    "step_50": 1.632,
+    "step_100": 1.5027
+  },
+  "wandb_run": "https://wandb.ai/developer_lunark-lunark-ai/kaidol-llm-finetuning/runs/brryct5m",
+  "notes": "Baseline test with 1K samples. Stable convergence observed. Ready for hyperparameter optimization (LR 2e-4→1e-4, alpha 16→32, grad_accum 4→8)."
+}
+```
+
+
+## Usage
+
+### 로드 방법 (Unsloth 사용)
+
+```python
+from unsloth import FastLanguageModel
+
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name="developer-lunark/kaidol-phase2a-test-1k",
+    max_seq_length=2048,
+    dtype=None,
+    load_in_4bit=True,
+)
+```
+
+### 추론 예시
+
+```python
+messages = [
+    {"role": "user", "content": "오늘 기분이 좋지 않아..."},
+]
+
+inputs = tokenizer.apply_chat_template(
+    messages,
+    tokenize=True,
+    add_generation_prompt=True,
+    return_tensors="pt"
+).to("cuda")
+
+outputs = model.generate(
+    inputs,
+    max_new_tokens=512,
+    temperature=0.7,
+    top_p=0.9,
+)
+
+response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(response)
+```
+
+## Dataset
+
+- **Phase 2**: RP Base Dataset (54K samples)
+  - Source: `developer-lunark/kaidol-phase2-rp-base-v0.1`
+  - Korean: 53% / English: 47%
+
+## Training Hardware
+
+- **GPU**: 4x NVIDIA RTX 5090 (32GB each)
+- **Training Time**: ~40 minutes
+- **Framework**: Unsloth + PyTorch 2.9.1 + CUDA 12.8
+
+## Limitations
+
+- 이 모델은 롤플레잉 및 공감 대화에 특화되어 있습니다
+- 일반적인 지식 질문이나 reasoning 작업에는 베이스 모델보다 성능이 낮을 수 있습니다
+- 한국어와 영어 외의 언어는 제한적으로 지원됩니다
+
+## Ethical Considerations
+
+- 이 모델은 연구 및 교육 목적으로 제작되었습니다
+- 상업적 사용 시 라이선스를 확인하세요
+- 생성된 콘텐츠의 품질과 적절성을 항상 검증하세요
+
+## Citation
+
+```bibtex
+@misc{kaidol-phase2a-test-1k,
+  author = {Developer Lunark},
+  title = {KAIDOL LLM Fine-tuning - PHASE2A-TEST-1K},
+  year = {2025},
+  publisher = {HuggingFace},
+  howpublished = {\url{https://huggingface.co/developer-lunark/kaidol-phase2a-test-1k}}
+}
+```
+
+## Model Card Contact
+
+- **Developer**: developer_lunark
+- **Repository**: https://github.com/developer-lunark/kaidol-llm-finetuning
+- **W&B Project**: https://wandb.ai/developer_lunark-lunark-ai/kaidol-llm-finetuning
+
+---
+
+Generated on 2025-11-18 09:24:35

adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3MoeForCausalLM",
+    "parent_library": "transformers.models.qwen3_moe.modeling_qwen3_moe",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/qwen3-30b-a3b-instruct-2507",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "o_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:a168a1beb52a7cf568ad655ee461ed927d85049ac799268f6e234338a623b9ca
+size 3380768360

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
+}

chat_template.jinja

@@ -0,0 +1,86 @@
+{%- 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 %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- 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" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- 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 %}

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": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_config.json

@@ -0,0 +1,62 @@
+{
+  "base_model": "unsloth/Qwen3-30B-A3B-Instruct-2507",
+  "phase": "phase2a-test-1k",
+  "training_config": {
+    "model": "Qwen3-30B-A3B-Instruct-2507",
+    "phase": "phase2a-test-1k",
+    "dataset": "phase2-rp-base-1k",
+    "num_samples": 1000,
+    "lora_rank": 16,
+    "lora_alpha": 16,
+    "lora_dropout": 0,
+    "learning_rate": 0.0002,
+    "batch_size": 2,
+    "gradient_accumulation_steps": 4,
+    "effective_batch_size": 32,
+    "max_steps": 100,
+    "warmup_steps": 10,
+    "max_seq_length": 2048,
+    "optimizer": "adamw_8bit",
+    "weight_decay": 0.01,
+    "lr_scheduler_type": "linear",
+    "precision": "bfloat16",
+    "device_map": "auto",
+    "gpus": "4x RTX 5090",
+    "training_time": "40 minutes",
+    "framework": "Unsloth 2025.11.3",
+    "target_modules": [
+      "q_proj",
+      "k_proj",
+      "v_proj",
+      "o_proj",
+      "gate_proj",
+      "up_proj",
+      "down_proj"
+    ]
+  },
+  "metrics": {
+    "training_loss": {
+      "initial": 2.3745,
+      "final": 1.5027,
+      "reduction_percent": 36.7
+    },
+    "training_metrics": {
+      "total_steps": 100,
+      "total_samples": 1000,
+      "training_time_seconds": 2380.49,
+      "training_time_minutes": 39.67,
+      "samples_per_second": 0.336,
+      "final_grad_norm": 0.1539,
+      "final_learning_rate": 0.0
+    },
+    "loss_progression": {
+      "step_5": 2.3745,
+      "step_10": 1.531,
+      "step_50": 1.632,
+      "step_100": 1.5027
+    },
+    "wandb_run": "https://wandb.ai/developer_lunark-lunark-ai/kaidol-llm-finetuning/runs/brryct5m",
+    "notes": "Baseline test with 1K samples. Stable convergence observed. Ready for hyperparameter optimization (LR 2e-4→1e-4, alpha 16→32, grad_accum 4→8)."
+  },
+  "upload_date": "2025-11-18T09:24:35.457118"
+}