Instructions to use im-sangwoon/chatprot-qwen2.5-32b-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use im-sangwoon/chatprot-qwen2.5-32b-lora 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, "im-sangwoon/chatprot-qwen2.5-32b-lora")

Transformers

How to use im-sangwoon/chatprot-qwen2.5-32b-lora with Transformers:

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

pipe = pipeline("text-generation", model="im-sangwoon/chatprot-qwen2.5-32b-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("im-sangwoon/chatprot-qwen2.5-32b-lora", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use im-sangwoon/chatprot-qwen2.5-32b-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "im-sangwoon/chatprot-qwen2.5-32b-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "im-sangwoon/chatprot-qwen2.5-32b-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/im-sangwoon/chatprot-qwen2.5-32b-lora

SGLang

How to use im-sangwoon/chatprot-qwen2.5-32b-lora 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 "im-sangwoon/chatprot-qwen2.5-32b-lora" \
    --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": "im-sangwoon/chatprot-qwen2.5-32b-lora",
		"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 "im-sangwoon/chatprot-qwen2.5-32b-lora" \
        --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": "im-sangwoon/chatprot-qwen2.5-32b-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use im-sangwoon/chatprot-qwen2.5-32b-lora with Docker Model Runner:
```
docker model run hf.co/im-sangwoon/chatprot-qwen2.5-32b-lora
```

im-sangwoon commited on Feb 25

Commit

0daf7bd

verified ·

1 Parent(s): 8b51c28

Fix training hardware: NVIDIA A6000 x 8

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -125,7 +125,7 @@ python -m vllm.entrypoints.openai.api_server \
 ### Hardware
-- **GPU:** NVIDIA GB10
 ### Framework Versions

 ### Hardware
+- **GPU:** NVIDIA A6000 x 8
 ### Framework Versions