Yida-Model-MM / README.md
rwang220's picture
Add Yida-Model-MM model card
12304dc verified
|
Raw History Blame Contribute Delete
2.64 kB
---
license: apache-2.0
language:
- zh
- en
pipeline_tag: text-generation
tags:
- medical
- qwen3
---
# Yida-Model-MM
Merged full-weight checkpoint of a Qwen3-14B LoRA supervised fine-tune. Hub files are merged `bfloat16` weights, not a PEFT adapter.
This model is for research and engineering evaluation. It is **not** a medical device and must not be used as the sole basis for clinical decisions.
## Model details
| Item | Value |
| --- | --- |
| Developed by | [rwang220](https://huggingface.co/rwang220) |
| Model type | Causal LM (`Qwen3ForCausalLM`) |
| Parameters | 14.77B (14,768,307,200) |
| Precision | bfloat16 |
| Architecture | 40 layers, hidden size 5120, GQA 40/8, intermediate size 17408, vocab 151936 |
| Context | `max_position_embeddings` 40,960. SFT max length 8,192 |
| License | Apache 2.0, inherited from Qwen3-14B |
## Training
Fine-tuned with ms-swift LoRA, then merged into full weights.
| Item | Value |
| --- | --- |
| Immediate base | Public [Qwen/Qwen3-14B](https://huggingface.co/Qwen/Qwen3-14B). |
| Run | `mm_sft_5_29/v0-20260529-080809` |
| LoRA | rank 16, alpha 32, dropout 0.05, targets `q/k/v/o/gate/up/down_proj` |
| Optim | AdamW, lr `1e-4`, cosine, warmup ratio 0.05 |
| Schedule | 3 epochs, 72,348 steps, max length 8192 |
| Batch | per-device 1, gradient accumulation 8 |
| Best eval loss | 0.6525 at step 71,500 |
| Final eval loss | 0.6525 |
| Final eval token acc | 0.7803 |
### Data
An internal, deduplicated Chinese medical instruction mix. Categories were capped; this is not the full uncapped set used by the DS variant.
## How to use
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "rwang220/Yida-Model-MM"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")
messages = [{"role": "user", "content": "请用通俗语言解释高血压的常见注意事项。"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=True)
inputs = tokenizer([text], return_tensors="pt").to(model.device)
output = model.generate(**inputs, max_new_tokens=1024, temperature=0.6, top_p=0.95, top_k=20)
print(tokenizer.decode(output[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))
```
```bash
vllm serve rwang220/Yida-Model-MM --reasoning-parser qwen3
```
## Limitations
- Can hallucinate guidelines, doses, diagnoses, and citations.
- Training data is internal and not released with this repository.
- Reported numbers are training eval loss and token accuracy only. No clinical benchmark is claimed.