From 7037757793e3fd5bcf929b1b901078db73ecc3d9 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sat, 5 Sep 2026 18:24:16 +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: NotoriousH2/Qwen3-0.6B-JSON-SFT Source: Original Platform --- .gitattributes | 36 +++++++++++++++++ README.md | 18 +++++++++ chat_template.jinja | 89 +++++++++++++++++++++++++++++++++++++++++ config.json | 63 +++++++++++++++++++++++++++++ generation_config.json | 12 ++++++ model.safetensors | 3 ++ tokenizer.json | 3 ++ tokenizer_config.json | 30 ++++++++++++++ train_meta.json | 91 ++++++++++++++++++++++++++++++++++++++++++ training_args.bin | 3 ++ 10 files changed, 348 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 create mode 100644 train_meta.json create mode 100644 training_args.bin 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..8133b04 --- /dev/null +++ b/README.md @@ -0,0 +1,18 @@ +--- +base_model: Qwen/Qwen3-0.6B +language: +- ko +pipeline_tag: text-generation +tags: +- trl +- sft +--- + +# Qwen3-0.6B-JSON-SFT + +회의록→JSON 추출 SFT (학생 0.6B 교체 실험, 시나리오 1) + +2026-07-19 sllm_practice 커리큘럼 개선 실험 산출물 (fa2e1ce의 experiments/results/REPORT.md 참조). +평가 지표는 json_eval.py (parse_rate / schema_compliance / semantics_pass_rate / field_f1_mean). + +Qwen/Qwen3-0.6B를 meeting_to_json_train.jsonl 1,199개로 full FT (no-think). old_eval 300개 기준 parse 98.0 / schema 96.3 / semantics 96.1 / field_F1 51.4% (base 41.6%). 학습 15.4분(A40). diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..01be9b3 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,89 @@ +{%- 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 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' }} + {%- 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('') and message.content.endswith('')) %} + {%- 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 '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-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\n' + reasoning_content.strip('\n') + '\n\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 %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- 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' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- '\n\n\n\n' }} + {%- endif %} +{%- endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..eca167b --- /dev/null +++ b/config.json @@ -0,0 +1,63 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3072, + "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" + ], + "max_position_embeddings": 40960, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "pad_token_id": 151645, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..b53c10e --- /dev/null +++ b/generation_config.json @@ -0,0 +1,12 @@ +{ + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151645, + "temperature": 0.6, + "top_k": 20, + "top_p": 0.95, + "transformers_version": "5.14.1" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..40e69d1 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad1e5e2de3c0c9610a0da953152ac12bef505f3ff916130536c8e51150d97547 +size 1192135096 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..c7afbed --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506 +size 11422650 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..866c19a --- /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, + "local_files_only": false, + "model_max_length": 131072, + "pad_token": "<|im_end|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/train_meta.json b/train_meta.json new file mode 100644 index 0000000..015d69e --- /dev/null +++ b/train_meta.json @@ -0,0 +1,91 @@ +{ + "train_sec": 927.9, + "max_length": 2816, + "think": false, + "epochs": 3, + "lr": 5e-06, + "log_history": [ + { + "eval_loss": 0.33602747321128845, + "eval_runtime": 8.8236, + "eval_samples_per_second": 12.127, + "eval_steps_per_second": 12.127, + "eval_entropy": 0.3295369472737624, + "eval_num_tokens": 4799219.0, + "eval_mean_token_accuracy": 0.9163304918280272, + "epoch": 2.625514403292181, + "step": 160 + }, + { + "loss": 0.34753003120422366, + "grad_norm": 2.71875, + "learning_rate": 1.4733707847247814e-07, + "entropy": 0.33421541005373, + "num_tokens": 4950630.0, + "mean_token_accuracy": 0.9143238365650177, + "epoch": 2.707818930041152, + "step": 165 + }, + { + "loss": 0.36279208660125734, + "grad_norm": 2.65625, + "learning_rate": 8.035874876982957e-08, + "entropy": 0.35163953751325605, + "num_tokens": 5099094.0, + "mean_token_accuracy": 0.9107247442007065, + "epoch": 2.7901234567901234, + "step": 170 + }, + { + "loss": 0.3491449594497681, + "grad_norm": 2.65625, + "learning_rate": 3.331468007589489e-08, + "entropy": 0.3429010361433029, + "num_tokens": 5250072.0, + "mean_token_accuracy": 0.9129759073257446, + "epoch": 2.8724279835390947, + "step": 175 + }, + { + "loss": 0.3632668018341064, + "grad_norm": 2.828125, + "learning_rate": 6.592445855863883e-09, + "entropy": 0.35197630524635315, + "num_tokens": 5402349.0, + "mean_token_accuracy": 0.9110080420970916, + "epoch": 2.954732510288066, + "step": 180 + }, + { + "eval_loss": 0.3358902931213379, + "eval_runtime": 8.9103, + "eval_samples_per_second": 12.009, + "eval_steps_per_second": 12.009, + "eval_entropy": 0.3294877093807559, + "eval_num_tokens": 5402349.0, + "eval_mean_token_accuracy": 0.9162927815847308, + "epoch": 2.954732510288066, + "step": 180 + }, + { + "eval_loss": 0.3358490765094757, + "eval_runtime": 9.0019, + "eval_samples_per_second": 11.886, + "eval_steps_per_second": 11.886, + "eval_entropy": 0.3295578314600704, + "eval_num_tokens": 5483673.0, + "eval_mean_token_accuracy": 0.9165575621284057, + "epoch": 3.0, + "step": 183 + }, + { + "train_runtime": 925.9091, + "train_samples_per_second": 3.146, + "train_steps_per_second": 0.198, + "total_flos": 1.4492276975075328e+16, + "train_loss": 0.38517201207374613, + "epoch": 3.0, + "step": 183 + } + ] +} \ No newline at end of file diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..775cc6d --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95a05f953115e145cb0a22d80eaece732e4a028e80473ee2054d7e4d3b4ac8b5 +size 5777