From 0dcc9f0f0607b17a25e242fd950b71a0d24f7fc9 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sat, 13 Jun 2026 15:50:18 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: g34634/qwen2.5-3b-memory-summary-v1 Source: Original Platform --- .gitattributes | 36 ++++++++ README.md | 181 +++++++++++++++++++++++++++++++++++++++++ chat_template.jinja | 54 ++++++++++++ config.json | 69 ++++++++++++++++ generation_config.json | 14 ++++ model.safetensors | 3 + tokenizer.json | 3 + tokenizer_config.json | 30 +++++++ 8 files changed, 390 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 chat_template.jinja create mode 100644 config.json create mode 100644 generation_config.json create mode 100644 model.safetensors create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..300f773 --- /dev/null +++ b/README.md @@ -0,0 +1,181 @@ +--- +language: +- en +- ko +license: apache-2.0 +base_model: Qwen/Qwen2.5-3B-Instruct +tags: +- memory +- multi-turn +- dialogue +- json-generation +- lora +- sft +pipeline_tag: text-generation +--- + +# Qwen2.5-3B Memory State Generator + +[Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct)를 멀티턴 대화에서 구조화된 메모리 상태를 추출하도록 파인튜닝한 모델입니다. + +멀티턴 대화 파이프라인에서 라우팅 및 검색 전에 가장 먼저 실행되며, 이후 컴포넌트(Router, RAG, LLM)가 활용할 수 있는 `memory_state` JSON을 생성합니다. + +``` +사용자 입력 → [Memory State Generator] → Router → LLM/VLM +``` + +--- + +## 모델 설명 + +| | | +|---|---| +| **베이스 모델** | Qwen/Qwen2.5-3B-Instruct | +| **파인튜닝 방식** | SFT + LoRA | +| **학습 데이터** | DialogSum + QMSum | +| **최대 시퀀스 길이** | 512 | +| **LoRA rank** | 16 | +| **GPU** | NVIDIA A100 40GB | +| **Epoch** | 3 | +| **최종 Validation Loss** | 0.693 | + +--- + +## 출력 형식 + +대화를 입력하면 아래 형식의 JSON을 출력합니다. + +```json +{ + "memory_state": { + "key_facts": ["사실1", "사실2"], + "unresolved_refs": ["불명확한 지시어나 대명사"], + "topic": "대화의 주제", + "turn_count": 5 + }, + "memory_summary": "지금까지의 대화를 한 문장으로 요약한 내용" +} +``` + +--- + +## 사용법 + +```python +from transformers import AutoTokenizer, AutoModelForCausalLM +import torch +import json + +model_id = "your-username/qwen2.5-3b-memory-summary-v1" + +tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True) +model = AutoModelForCausalLM.from_pretrained( + model_id, + torch_dtype=torch.bfloat16, + device_map="auto", + trust_remote_code=True +) + +SYSTEM_PROMPT = """You are a Memory State Generator in a multi-turn dialogue system. +Given a conversation, extract and output a structured memory state as JSON. + +Output format (strictly follow this): +{ + "memory_state": { + "key_facts": ["fact1", "fact2"], + "unresolved_refs": ["any unclear references or pronouns"], + "topic": "main topic of the conversation", + "turn_count": + }, + "memory_summary": "One concise sentence summarizing the conversation so far." +} + +Output only valid JSON. No explanation, no markdown.""" + +dialogue = """ +A: RAG 파이프라인 구현 완료했어요. +B: 모델은 어떤 걸 쓰기로 했어요? +A: Qwen2.5-3B-Instruct로 결정했어요. LoRA로 파인튜닝할 예정입니다. +""" + +messages = [ + {"role": "system", "content": SYSTEM_PROMPT}, + {"role": "user", "content": f"Conversation:\n{dialogue}"} +] + +input_text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) +inputs = tokenizer(input_text, return_tensors="pt").to(model.device) + +with torch.no_grad(): + outputs = model.generate( + **inputs, + max_new_tokens=512, + temperature=0.1, + do_sample=True, + pad_token_id=tokenizer.eos_token_id + ) + +response = tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True) +parsed = json.loads(response) +print(json.dumps(parsed, indent=2, ensure_ascii=False)) +``` + +--- + +## 학습 정보 + +### 데이터 + +| 데이터셋 | 크기 | 설명 | +|---|---|---| +| [DialogSum](https://huggingface.co/datasets/knkarthick/dialogsum) | 13,031개 | 일상 대화 + 사람이 작성한 요약문 | +| [QMSum](https://huggingface.co/datasets/pszemraj/qmsum-cleaned) | 686개 | 회의록 + query 기반 요약 쌍 | + +두 데이터셋 모두 `memory_state JSON` 형식으로 변환하여 SFT 학습에 사용했습니다. + +### 학습 설정 + +```python +LoraConfig( + r=16, + lora_alpha=32, + lora_dropout=0.05, + target_modules=["q_proj", "k_proj", "v_proj", "o_proj", + "gate_proj", "up_proj", "down_proj"], +) + +SFTConfig( + num_train_epochs=3, + per_device_train_batch_size=1, + gradient_accumulation_steps=16, + learning_rate=2e-4, + lr_scheduler_type="cosine", + max_seq_length=512, + bf16=True, +) +``` + +### 학습 Loss + +| Step | Training Loss | Validation Loss | +|---|---|---| +| 100 | 14.578 | 0.896 | +| 500 | 12.919 | 0.804 | +| 1000 | 11.361 | 0.734 | +| 1500 | 10.437 | 0.694 | +| 2000 | 9.783 | 0.694 | +| 2400 | 9.635 | 0.693 | + +--- + +## 한계점 + +- 대화 형식에 따라 `turn_count` 추출이 부정확할 수 있습니다 +- `key_facts`가 구체적인 사실 추출보다 추상적인 요약에 가깝게 나오는 경우가 있습니다 — synthetic 데이터 추가 학습으로 개선 예정입니다 +- 짧은~중간 길이 대화에 최적화되어 있습니다 (최대 512 토큰) + +--- + +## 라이선스 + +Apache 2.0 diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..bdf7919 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,54 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }} + {%- endif %} + {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0]['role'] == 'system' %} + {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }} + {%- else %} + {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.content %} + {{- '\n' + message.content }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- 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 %} diff --git a/config.json b/config.json new file mode 100644 index 0000000..7f1504f --- /dev/null +++ b/config.json @@ -0,0 +1,69 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "bfloat16", + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 11008, + "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": 32768, + "max_window_layers": 70, + "model_type": "qwen2", + "num_attention_heads": 16, + "num_hidden_layers": 36, + "num_key_value_heads": 2, + "pad_token_id": null, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.0.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..a3498e8 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "repetition_penalty": 1.05, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.0.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..6816ff9 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d36d214a64b5d7188377c54ded87a1c61a7c2fe49050a4119ba2573bd9b65a3 +size 6171927112 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..34510ff --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8 +size 11421892 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..3615ef7 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,30 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_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|>" + ], + "is_local": true, + "model_max_length": 131072, + "model_specific_special_tokens": {}, + "pad_token": "<|im_end|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}