Instructions to use codefuse-ai/SWE-CARE-RM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use codefuse-ai/SWE-CARE-RM with Transformers:

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

pipe = pipeline("text-generation", model="codefuse-ai/SWE-CARE-RM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("codefuse-ai/SWE-CARE-RM")
model = AutoModelForCausalLM.from_pretrained("codefuse-ai/SWE-CARE-RM", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use codefuse-ai/SWE-CARE-RM with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/codefuse-ai/SWE-CARE-RM

SGLang

How to use codefuse-ai/SWE-CARE-RM 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 "codefuse-ai/SWE-CARE-RM" \
    --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": "codefuse-ai/SWE-CARE-RM",
		"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 "codefuse-ai/SWE-CARE-RM" \
        --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": "codefuse-ai/SWE-CARE-RM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use codefuse-ai/SWE-CARE-RM with Docker Model Runner:
```
docker model run hf.co/codefuse-ai/SWE-CARE-RM
```

SWE-CARE-RM

Commit History

Apr 9

09:57
Delete eval_result.json

Elvis-t9

Verified signature
dadf0d1
09:56
Update reward_config.json

Elvis-t9

Verified signature
fcdf090
09:54
update model card⁠

Elvis-t9

Verified signature
9050771
09:49
Update README.md⁠

Elvis-t9

Verified signature
75eae10
09:34
Upload folder using huggingface_hub

Geralt-Targaryen

Verified signature
6fc77cb
09:31
Upload folder using huggingface_hub

Geralt-Targaryen

Verified signature
23b32ab
09:23
initial commit

Geralt-Targaryen

Verified signature
3c5894b

Commit History

Apr 9

Delete eval_result.json

Update reward_config.json

update model card⁠

Update README.md⁠

Upload folder using huggingface_hub

Upload folder using huggingface_hub

initial commit