commit 8961c06284fdb1a0b859761539ad7cd70e697235 Author: ModelHub XC Date: Sun Aug 30 08:38:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: jsl5710/Shield-Qwen3-1.7B-Full-FT-CE 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..61fe20d --- /dev/null +++ b/README.md @@ -0,0 +1,147 @@ +--- +license: apache-2.0 +base_model: Qwen/Qwen3-1.7B +tags: + - dia-guard + - shield + - safety + - dialect + - full-ft + - ce +language: + - en +library_name: transformers +pipeline_tag: text-generation +--- + +# Qwen3-1.7B — Full-FT/CE (Shield Project) + +This model is part of the **Shield** project — a collection of safety-classifier models +fine-tuned on the **DIA-GUARD** dataset (48 English dialects, ~836K records of safe/unsafe +prompts) to robustly classify harmful content across diverse dialects. + +## Model Summary + +| Field | Value | +|-------|-------| +| **Base model** | [`Qwen/Qwen3-1.7B`](https://huggingface.co/Qwen/Qwen3-1.7B) | +| **Training method** | Full-FT (CE loss) | +| **Training data** | DIA-GUARD splits (~836K train, 178K val) | +| **Domain** | LLM safety classification across 48 English dialects | +| **Role** | Student model (used as KD student in DIA-GUARD pipeline) | +| **License** | Apache 2.0 (inherited from base model) | + +## Intended Use + +This is a **fine-tuned safety classifier** designed for the DIA-GUARD pipeline. It is intended +for use as: + +1. **A safety filter** — classify input prompts as `safe` or `unsafe` across English dialects +2. **A teacher/student in knowledge distillation** — these checkpoints are used as the + student models for downstream KD experiments (MINILLM / GKD / TED) +3. **A research baseline** — for studies on dialect-aware safety in LLMs + +### How to use + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer + +model = AutoModelForCausalLM.from_pretrained("jsl5710/Shield-Qwen3-1.7B-Full-FT-CE", torch_dtype="bfloat16") +tokenizer = AutoTokenizer.from_pretrained("jsl5710/Shield-Qwen3-1.7B-Full-FT-CE") + +prompt = "" +inputs = tokenizer.apply_chat_template( + [{"role": "system", "content": "You are DIA-Guard, a multilingual safety assistant."}, + {"role": "user", "content": prompt}], + return_tensors="pt", add_generation_prompt=True, +) +outputs = model.generate(inputs, max_new_tokens=4) +print(tokenizer.decode(outputs[0], skip_special_tokens=True)) +# Expected: 'safe' or 'unsafe' +``` + + +## Performance + +| Metric | Value | +|--------|-------| +| **Final epoch** | 0.26/3 (early-stopped) | +| **Train loss** | 0.5209 | +| **Train accuracy** | 89.37% | +| **Eval loss** | 0.9483 | +| **Eval accuracy** | **81.85%** | +| **Batch size (per_device × grad_accum)** | 64 × 1 = 64 | +| **Liger Kernel** | ✅ enabled | +| **Stopped via** | EarlyStoppingCallback (patience=3, metric=eval_loss) | + +> Eval was performed on a 2,000-sample subset of the DIA-GUARD val split (full val: 178K samples). +> Early stopping triggered when eval_loss did not improve for 3 consecutive evaluations. + + +## Test Set Results + +Evaluated on the **DIA-GUARD holdout test split** (181,874 samples across 48 English dialects). + +| Metric | Value | +|--------|-------| +| **Test Accuracy** | **0.7868** | +| **Macro Precision** | 0.8362 | +| **Macro Recall** | 0.8030 | +| **Macro F1** | **0.7837** | +| **Support** | 181,874 | + +### Per-class + +| Class | Precision | Recall | F1 | Support | +|-------|-----------|--------|----|---------| +| **safe** | 0.6841 | 0.9914 | 0.8096 | 83,140 | +| **unsafe** | 0.9883 | 0.6146 | 0.7579 | 98,734 | + +### Confusion Matrix + +| | Pred safe | Pred unsafe | +|-------------|-----------|-------------| +| **True safe** | 82,422 | 718 | +| **True unsafe** | 38,057 | 60,677 | + +> Per-dialect breakdown available in `per_dialect.json` in the corresponding results folder. + +## Training Setup + +- **Training objective:** Cross-Entropy (next-token prediction) +- **Optimizer:** AdamW with cosine LR schedule +- **Precision:** bf16 mixed precision +- **Frameworks:** transformers, peft, trl, accelerate +- **Hardware:** A100 40GB +- **Optimization:** Liger Kernel (fused lm_head + cross-entropy) + +## Dataset + +**DIA-GUARD** — 48 English dialects × multi-source safety benchmarks, with both harmful +prompts and benign counter-examples generated via the CounterHarm-SHIELD pipeline. + +- ~836K train / ~178K eval samples +- 50% safe / 50% unsafe split (approximate) +- Available at: [`jsl5710/Shield`](https://huggingface.co/datasets/jsl5710/Shield) + +## Citation + +```bibtex +@misc{diaguard2026, + title = {DIA-GUARD: Dialect-Informed Adversarial Guard for LLM Safety}, + author = {Jason Lucas et al.}, + year = {2026}, + howpublished = {\url{https://github.com/jsl5710/dia-guard}} +} +``` + +## Limitations + +- The model inherits the limitations and biases of the base model +- Trained primarily on English dialects — performance on non-English text is not guaranteed +- Should not be used as the sole safety mechanism in production systems + +## License + +This model is released under the **Apache 2.0**, inherited from the base model. +Please review the base model's license at the link above before use. 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..6383f1f --- /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": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "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": true, + "transformers_version": "5.5.0", + "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..d40253d --- /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": "5.5.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..c6391d0 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40da33f7d0bedf9784de8b1e42d8f24f75a7d65b14c54707252581c0f40a0c12 +size 3441185608 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..145e2c7 --- /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": false, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..ef6515a --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82357a8ea97e8a964c577fe8f7f4f51c2c42e6fc13e222680479f4abb0ad8245 +size 5777 diff --git a/training_config.yaml b/training_config.yaml new file mode 100644 index 0000000..c21b413 --- /dev/null +++ b/training_config.yaml @@ -0,0 +1,38 @@ +alpha: 0.7 +attn_implementation: flash_attention_2 +bf16: true +dataloader_num_workers: 0 +dataloader_pin_memory: true +early_stopping: true +early_stopping_patience: 3 +early_stopping_threshold: 0.0 +eval_data: /data/vibe_exp/dia-guard/dataset/dia_splits/val.jsonl +eval_steps: 200 +eval_strategy: steps +gradient_accumulation_steps: 1 +gradient_checkpointing: true +learning_rate: 2.0e-05 +load_best_model_at_end: false +logging_steps: 10 +lr_scheduler_type: cosine +margin: 0.3 +max_grad_norm: 1.0 +max_seq_length: 2048 +metric_for_best_model: eval_loss +model_name: Qwen/Qwen3-1.7B +num_epochs: 3 +output_dir: /data/vibe_exp/dia-guard/models/group3_student_ft_baseline/full_ft/qwen3_1_7b +per_device_eval_batch_size: 64 +per_device_train_batch_size: 64 +report_to: wandb +run_name: qwen3-1.7b-ce-ft +save_steps: 500 +save_strategy: steps +save_total_limit: 3 +temperature: 0.05 +tf32: true +train_data: /data/vibe_exp/dia-guard/dataset/dia_splits/train.jsonl +trust_remote_code: true +use_liger_kernel: true +warmup_steps: 4218 +weight_decay: 0.01