初始化项目，由ModelHub XC社区提供模型
Model: jsl5710/Shield-SmolLM2-1.7B-Full-FT-CE Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.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
|
||||
147
README.md
Normal file
147
README.md
Normal file
@@ -0,0 +1,147 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
base_model: HuggingFaceTB/SmolLM2-1.7B-Instruct
|
||||
tags:
|
||||
- dia-guard
|
||||
- shield
|
||||
- safety
|
||||
- dialect
|
||||
- full-ft
|
||||
- ce
|
||||
language:
|
||||
- en
|
||||
library_name: transformers
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
|
||||
# SmolLM2-1.7B — 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** | [`HuggingFaceTB/SmolLM2-1.7B-Instruct`](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-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** | 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-SmolLM2-1.7B-Full-FT-CE", torch_dtype="bfloat16")
|
||||
tokenizer = AutoTokenizer.from_pretrained("jsl5710/Shield-SmolLM2-1.7B-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** | 0.60/3 (early-stopped) |
|
||||
| **Train loss** | 0.6234 |
|
||||
| **Train accuracy** | 82.67% |
|
||||
| **Eval loss** | 0.7843 |
|
||||
| **Eval accuracy** | **77.93%** |
|
||||
| **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** | **0.7481** |
|
||||
| **Macro Precision** | 0.7732 |
|
||||
| **Macro Recall** | 0.7601 |
|
||||
| **Macro F1** | **0.7467** |
|
||||
| **Support** | 181,874 |
|
||||
|
||||
### Per-class
|
||||
|
||||
| Class | Precision | Recall | F1 | Support |
|
||||
|-------|-----------|--------|----|---------|
|
||||
| **safe** | 0.6663 | 0.8996 | 0.7655 | 83,140 |
|
||||
| **unsafe** | 0.8801 | 0.6206 | 0.7279 | 98,734 |
|
||||
|
||||
### Confusion Matrix
|
||||
|
||||
| | Pred safe | Pred unsafe |
|
||||
|-------------|-----------|-------------|
|
||||
| **True safe** | 74,791 | 8,349 |
|
||||
| **True unsafe** | 37,461 | 61,273 |
|
||||
|
||||
> 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.
|
||||
6
chat_template.jinja
Normal file
6
chat_template.jinja
Normal file
@@ -0,0 +1,6 @@
|
||||
{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
|
||||
You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
|
||||
' }}{% endif %}{{'<|im_start|>' + message['role'] + '
|
||||
' + message['content'] + '<|im_end|>' + '
|
||||
'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
|
||||
' }}{% endif %}
|
||||
43
config.json
Normal file
43
config.json
Normal file
@@ -0,0 +1,43 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 2,
|
||||
"head_dim": 64,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 8192,
|
||||
"max_position_embeddings": 8192,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 24,
|
||||
"num_key_value_heads": 32,
|
||||
"pad_token_id": 2,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 130000,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"tie_word_embeddings": true,
|
||||
"transformers.js_config": {
|
||||
"dtype": "q4",
|
||||
"kv_cache_dtype": {
|
||||
"fp16": "float16",
|
||||
"q4f16": "float16"
|
||||
},
|
||||
"use_external_data_format": {
|
||||
"model.onnx": true,
|
||||
"model_fp16.onnx": true
|
||||
}
|
||||
},
|
||||
"transformers_version": "5.5.0",
|
||||
"use_cache": false,
|
||||
"vocab_size": 49152
|
||||
}
|
||||
9
generation_config.json
Normal file
9
generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": [
|
||||
2
|
||||
],
|
||||
"pad_token_id": 2,
|
||||
"transformers_version": "5.5.0"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:72fbe1d1f4c45903ce2c6c0f26950f3e2f230ef48942f49d8f77ce7eaedacb0a
|
||||
size 3422777952
|
||||
244965
tokenizer.json
Normal file
244965
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
19
tokenizer_config.json
Normal file
19
tokenizer_config.json
Normal file
@@ -0,0 +1,19 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": "<|im_start|>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>"
|
||||
],
|
||||
"is_local": false,
|
||||
"model_max_length": 8192,
|
||||
"pad_token": "<|im_end|>",
|
||||
"padding_side": "right",
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"unk_token": "<|endoftext|>",
|
||||
"vocab_size": 49152
|
||||
}
|
||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:64a61d027d481eefd8895a7600bd01f30cd3e27c9832c94e501b39dd4a10dfca
|
||||
size 5777
|
||||
38
training_config.yaml
Normal file
38
training_config.yaml
Normal file
@@ -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: HuggingFaceTB/SmolLM2-1.7B-Instruct
|
||||
num_epochs: 3
|
||||
output_dir: /data/vibe_exp/dia-guard/models/group3_student_ft_baseline/full_ft/smollm2_1_7b_instruct
|
||||
per_device_eval_batch_size: 64
|
||||
per_device_train_batch_size: 64
|
||||
report_to: wandb
|
||||
run_name: smollm2-1.7b-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: false
|
||||
use_liger_kernel: true
|
||||
warmup_steps: 4218
|
||||
weight_decay: 0.01
|
||||
Reference in New Issue
Block a user