---
language: en
license: other
library_name: peft
base_model: Qwen/Qwen2.5-32B-Instruct
pipeline_tag: text-generation
tags:
- lora
- peft
- transformers
- qwen2.5
- conversational
---

# DeepSupport Warm ❤️‍🩹 - LoRA adapter
This repository provides a LoRA adapter for DeepSupport Warm, an emotional-holding companion that offers gentle reflection and warm support without rushing into what to do next.

## What it does ✨
DeepSupport Warm is designed to help users feel held and less alone in the moment:

- Validate and name feelings without judging  
- Stay with emotion first before problem-solving  
- Offer gentle grounding and a small next step only if you want 



## Quick start 🚀
### 1) Install
```bash
pip install transformers peft accelerate torch
```

### 2) Load base model and LoRA adapter
```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

base_id = "Qwen/Qwen2.5-32B-Instruct" # Base model we used. You may replace it with another compatible base model
lora_id = "Yukyin/deepsupport-warm-lora-oss"

tokenizer = AutoTokenizer.from_pretrained(base_id, trust_remote_code=True)
base = AutoModelForCausalLM.from_pretrained(
    base_id,
    torch_dtype=torch.float16,
    device_map="auto",
    trust_remote_code=True,
)

model = PeftModel.from_pretrained(base, lora_id)
model.eval()

messages = [
    {"role": "user", "content": "我最近压力很大，感觉自己一直在被否定。"},
]

inputs = tokenizer.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_tensors="pt",
).to(model.device)

with torch.no_grad():
    out = model.generate(
        inputs,
        max_new_tokens=256,
        do_sample=True,
        temperature=0.85,
        top_p=0.9,
        repetition_penalty=1.12,
        no_repeat_ngram_size=4,
    )

print(tokenizer.decode(out[0], skip_special_tokens=True))
```


## Training data and release notes 📊
- This OSS LoRA adapter is trained on de-identified versions of the original data.
- The original internal LoRA adapter was trained on non-de-identified data and cannot be open-sourced at this time.
- More details and examples are provided in the [GitHub repo](https://github.com/Yukyin/DeepSupport).


## Safety and privacy ⚠️
This project is intended for supportive conversation only.  
It does not provide professional advice, diagnosis, or therapy. Please seek qualified professional help when needed.


## License 📜
This adapter is released for noncommercial use. See the [GitHub repo](https://github.com/Yukyin/DeepSupport) for the full license text and commercial licensing terms.


## Citation 📚
```bibtex
@software{deepsupport_warm_2026,
  author  = {Yuyan Chen},
  title   = {DeepSupport Warm: An emotional-holding companion for supportive dialogue},
  year    = {2026},
  version = {oss},
  url     = {\url{https://github.com/Yukyin/DeepSupport/DeepSupport_Warm}}
}
```

## Links
- GitHub: https://github.com/Yukyin/DeepSupport
- LoRA adapter: https://huggingface.co/Yukyin/deepsupport-warm-lora-oss