Instructions to use Yukyin/deepsupport-warm-lora-oss with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Yukyin/deepsupport-warm-lora-oss with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-32B-Instruct")
model = PeftModel.from_pretrained(base_model, "Yukyin/deepsupport-warm-lora-oss")

Transformers

How to use Yukyin/deepsupport-warm-lora-oss with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Yukyin/deepsupport-warm-lora-oss")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Yukyin/deepsupport-warm-lora-oss", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Yukyin/deepsupport-warm-lora-oss with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Yukyin/deepsupport-warm-lora-oss"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Yukyin/deepsupport-warm-lora-oss",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Yukyin/deepsupport-warm-lora-oss

SGLang

How to use Yukyin/deepsupport-warm-lora-oss with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Yukyin/deepsupport-warm-lora-oss" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Yukyin/deepsupport-warm-lora-oss",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Yukyin/deepsupport-warm-lora-oss" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Yukyin/deepsupport-warm-lora-oss",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Yukyin/deepsupport-warm-lora-oss with Docker Model Runner:
```
docker model run hf.co/Yukyin/deepsupport-warm-lora-oss
```

deepsupport-warm-lora-oss / README.md

nielsr HF Staff

Add paper and Ekova repo links to model card

4034041 verified 8 days ago

3.42 kB

base_model: Qwen/Qwen2.5-32B-Instruct
language: en
library_name: peft
license: other
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.

This adapter is part of the multi-persona Ekova personality-support system described in Ekova: A Personality-Support Agent for Self-Discovery Dialogue. The Ekova project repository is available at https://github.com/Yukyin/Ekova.

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

pip install transformers peft accelerate torch

2) Load base model and LoRA adapter

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.

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 for the full license text and commercial licensing terms.

Citation 📚

@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}}
}

Yukyin
/

deepsupport-warm-lora-oss