初始化项目，由ModelHub XC社区提供模型

Model: jsl5710/Shield-Llama-3.2-1B-Full-FT-CE Source: Original Platform
2026-06-12 16:06:16 +08:00
commit 6660aef245
10 changed files with 388 additions and 0 deletions
--- a/.gitattributes
+++ 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
--- a/README.md
+++ b/README.md
@@ -0,0 +1,147 @@
+---
+license: llama3.2
+base_model: meta-llama/Llama-3.2-1B-Instruct
+tags:
+  - dia-guard
+  - shield
+  - safety
+  - dialect
+  - full-ft
+  - ce
+language:
+  - en
+library_name: transformers
+pipeline_tag: text-generation
+---
+
+# Llama-3.2-1B — 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** | [`meta-llama/Llama-3.2-1B-Instruct`](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) |
+| **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** | Llama 3.2 Community License (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-Llama-3.2-1B-Full-FT-CE", torch_dtype="bfloat16")
+tokenizer = AutoTokenizer.from_pretrained("jsl5710/Shield-Llama-3.2-1B-Full-FT-CE")
+
+prompt = "<your prompt here>"
+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** | 0.71/3 (early-stopped) |
+| **Train loss** | 0.5147 |
+| **Train accuracy** | — |
+| **Eval loss** | 0.6634 |
+| **Eval accuracy** | **85.67%** |
+| **Batch size (per_device × grad_accum)** | 96 × 1 = 96 |
+| **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** | **0.9644** |
+| **Macro Precision** | 0.9636 |
+| **Macro Recall** | 0.9668 |
+| **Macro F1** | **0.9642** |
+| **Support** | 181,874 |
+
+### Per-class
+
+| Class | Precision | Recall | F1 | Support |
+|-------|-----------|--------|----|---------|
+| **safe** | 0.9311 | 0.9956 | 0.9623 | 83,140 |
+| **unsafe** | 0.9961 | 0.9380 | 0.9662 | 98,734 |
+
+### Confusion Matrix
+
+|             | Pred safe | Pred unsafe |
+|-------------|-----------|-------------|
+| **True safe** | 82,778 | 362 |
+| **True unsafe** | 6,121 | 92,613 |
+
+> 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 **Llama 3.2 Community License**, inherited from the base model.
+Please review the base model's license at the link above before use.
--- a/chat_template.jinja
+++ b/chat_template.jinja
@@ -0,0 +1,93 @@
+{{- bos_token }}
+{%- if custom_tools is defined %}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if not tools_in_user_message is defined %}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- if strftime_now is defined %}
+        {%- set date_string = strftime_now("%d %b %Y") %}
+    {%- else %}
+        {%- set date_string = "26 Jul 2024" %}
+    {%- endif %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content']|trim %}
+    {%- set messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+{%- endif %}
+
+{#- System message #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if tools is not none %}
+    {{- "Environment: ipython\n" }}
+{%- endif %}
+{{- "Cutting Knowledge Date: December 2023\n" }}
+{{- "Today Date: " + date_string + "\n\n" }}
+{%- if tools is not none and not tools_in_user_message %}
+    {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+{%- endif %}
+{{- system_message }}
+{{- "<|eot_id|>" }}
+
+{#- Custom tools are passed in a user message with some extra guidance #}
+{%- if tools_in_user_message and not tools is none %}
+    {#- Extract the first user message so we can plug it in here #}
+    {%- if messages | length != 0 %}
+        {%- set first_user_message = messages[0]['content']|trim %}
+        {%- set messages = messages[1:] %}
+    {%- else %}
+        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
+{%- endif %}
+    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot_id|>"}}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
+    {%- elif 'tool_calls' in message %}
+        {%- if not message.tool_calls|length == 1 %}
+            {{- raise_exception("This model only supports single tool-calls at once!") }}
+        {%- endif %}
+        {%- set tool_call = message.tool_calls[0].function %}
+        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+        {{- '{"name": "' + tool_call.name + '", ' }}
+        {{- '"parameters": ' }}
+        {{- tool_call.arguments | tojson }}
+        {{- "}" }}
+        {{- "<|eot_id|>" }}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "bfloat16",
+  "eos_token_id": 128009,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128009,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_theta": 500000.0,
+    "rope_type": "llama3"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.0",
+  "use_cache": false,
+  "vocab_size": 128256
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128009,
+    128001,
+    128008,
+    128009
+  ],
+  "pad_token_id": 128009,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "5.5.0"
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16e63ab68c1cbdd30977390d71ef18794e18fffb695eb36a8820e0b36b35166f
+size 2471645608
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "is_local": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "TokenizersBackend"
+}
--- a/training_args.bin
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05d22369a0e6dd627b1f730b89fcbc9dc467e6e13a957fd6e09a968e25fe7098
+size 5777
--- a/training_config.yaml
+++ 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: 3.0e-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: meta-llama/Llama-3.2-1B-Instruct
+num_epochs: 3
+output_dir: /data/vibe_exp/dia-guard/models/group3_student_ft_baseline/full_ft/llama_3_2_1b_instruct
+per_device_eval_batch_size: 96
+per_device_train_batch_size: 96
+report_to: wandb
+run_name: llama-3.2-1b-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: false
+use_liger_kernel: true
+warmup_steps: 4218
+weight_decay: 0.01