commit a1755349b3b8fe807a89d0775aa1ea080217845e Author: ModelHub XC Date: Sun Aug 2 16:47:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: lldois/v33_task_arith_v29_live55_r325 Source: Original Platform 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..8897611 --- /dev/null +++ b/README.md @@ -0,0 +1,58 @@ +--- +library_name: transformers +license: other +base_model: lldois/v19_v15_dualmode_fast_lr5e6_ep055 +tags: +- llama-factory +- full +- generated_from_trainer +model-index: +- name: v29_v19_user_world_guard_lr8e7_ep018 + results: [] +--- + + + +# v29_v19_user_world_guard_lr8e7_ep018 + +This model is a fine-tuned version of [lldois/v19_v15_dualmode_fast_lr5e6_ep055](https://huggingface.co/lldois/v19_v15_dualmode_fast_lr5e6_ep055) on the exp_v19_user_world_guard_no_template dataset. + +## Model description + +More information needed + +## Intended uses & limitations + +More information needed + +## Training and evaluation data + +More information needed + +## Training procedure + +### Training hyperparameters + +The following hyperparameters were used during training: +- learning_rate: 8e-07 +- train_batch_size: 1 +- eval_batch_size: 8 +- seed: 202607291 +- gradient_accumulation_steps: 4 +- total_train_batch_size: 4 +- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments +- lr_scheduler_type: cosine +- lr_scheduler_warmup_steps: 0.02 +- num_epochs: 0.18 + +### Training results + + + +### Framework versions + +- Transformers 5.6.0 +- Pytorch 2.7.1+cu126 +- Datasets 4.0.0 +- Tokenizers 0.22.2 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..c4eb20b --- /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": 151643, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "5.6.0", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 176253 +} diff --git a/experiment_recipe.json b/experiment_recipe.json new file mode 100644 index 0000000..9b9bb95 --- /dev/null +++ b/experiment_recipe.json @@ -0,0 +1,21 @@ +{ + "created_at": "2026-07-13 03:38:30", + "name": "v33_task_arith_v29_live55_r325", + "method": "task_arithmetic", + "formula": "theta_v29 + 0.55*(theta_v31-theta_v29) + 0.25*(theta_v32-theta_v29)", + "base": "/home/ll/llm4rec/experiments/outputs/v29_v19_user_world_guard_lr8e7_ep018", + "experts": [ + { + "path": "/home/ll/llm4rec/experiments/outputs/v31_v29_live_specialist_r3_lr12e6_ep035", + "task_vector_scale": 0.55 + }, + { + "path": "/home/ll/llm4rec/experiments/outputs/v32_v29_balanced_r3_draft_lr8e7_ep020", + "task_vector_scale": 0.25 + } + ], + "rationale": "Approximate OneReason specialize-then-unify without leaderboard labels: retain 20% explicit v29 weight, emphasize the live-domain expert, and add a smaller balanced R3 cognition delta.", + "cot_policy": "All checkpoints descend from the CoT-native v29/v19 line; v7 is not used.", + "reproduce": "demo/LLaMA-Factory/.venv/bin/python experiments/task_arithmetic.py --name v33_task_arith_v29_live55_r325 --overwrite", + "runtime_seconds": 2.11 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..cf5bf49 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,12 @@ +{ + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.6, + "top_k": 20, + "top_p": 0.95, + "transformers_version": "5.6.0" +} diff --git a/merge_results.json b/merge_results.json new file mode 100644 index 0000000..9b9bb95 --- /dev/null +++ b/merge_results.json @@ -0,0 +1,21 @@ +{ + "created_at": "2026-07-13 03:38:30", + "name": "v33_task_arith_v29_live55_r325", + "method": "task_arithmetic", + "formula": "theta_v29 + 0.55*(theta_v31-theta_v29) + 0.25*(theta_v32-theta_v29)", + "base": "/home/ll/llm4rec/experiments/outputs/v29_v19_user_world_guard_lr8e7_ep018", + "experts": [ + { + "path": "/home/ll/llm4rec/experiments/outputs/v31_v29_live_specialist_r3_lr12e6_ep035", + "task_vector_scale": 0.55 + }, + { + "path": "/home/ll/llm4rec/experiments/outputs/v32_v29_balanced_r3_draft_lr8e7_ep020", + "task_vector_scale": 0.25 + } + ], + "rationale": "Approximate OneReason specialize-then-unify without leaderboard labels: retain 20% explicit v29 weight, emphasize the live-domain expert, and add a smaller balanced R3 cognition delta.", + "cot_policy": "All checkpoints descend from the CoT-native v29/v19 line; v7 is not used.", + "reproduce": "demo/LLaMA-Factory/.venv/bin/python experiments/task_arithmetic.py --name v33_task_arith_v29_live55_r325 --overwrite", + "runtime_seconds": 2.11 +} \ No newline at end of file diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..4aa5c26 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0b0407437f6bca3284a3d2d116d87487108c3e572e03f15570a4e23a1385a17 +size 1602902800 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..8aee134 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd4d15f596979aecbc11ba12668cb21c9fb8452ce1235cd9d7878cc950170421 +size 16016554 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..35d445f --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,16 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "is_local": true, + "local_files_only": false, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}