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
```

Add paper and Ekova repo links to model card

by nielsr HF Staff - opened 8 days ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-3

Files changed (1) hide show

README.md +6 -3

README.md CHANGED Viewed

@@ -1,8 +1,8 @@
 ---
 language: en
-license: other
 library_name: peft
-base_model: Qwen/Qwen2.5-32B-Instruct
 pipeline_tag: text-generation
 tags:
 - lora
@@ -15,6 +15,8 @@ tags:
 # 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:
@@ -104,4 +106,5 @@ This adapter is released for noncommercial use. See the [GitHub repo](https://gi
 ## Links
 - GitHub: https://github.com/Yukyin/DeepSupport
-- LoRA adapter: https://huggingface.co/Yukyin/deepsupport-warm-lora-oss

 ---
+base_model: Qwen/Qwen2.5-32B-Instruct
 language: en
 library_name: peft
+license: other
 pipeline_tag: text-generation
 tags:
 - lora
 # 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](https://huggingface.co/papers/2608.00478). 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:
 ## Links
 - GitHub: https://github.com/Yukyin/DeepSupport
+- GitHub (Ekova): https://github.com/Yukyin/Ekova
+- LoRA adapter: https://huggingface.co/Yukyin/deepsupport-warm-lora-oss