Instructions to use purewhite42/HAR_CoPA_Cycle2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use purewhite42/HAR_CoPA_Cycle2 with Transformers:

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

pipe = pipeline("text-generation", model="purewhite42/HAR_CoPA_Cycle2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("purewhite42/HAR_CoPA_Cycle2")
model = AutoModelForCausalLM.from_pretrained("purewhite42/HAR_CoPA_Cycle2")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use purewhite42/HAR_CoPA_Cycle2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "purewhite42/HAR_CoPA_Cycle2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "purewhite42/HAR_CoPA_Cycle2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/purewhite42/HAR_CoPA_Cycle2

SGLang

How to use purewhite42/HAR_CoPA_Cycle2 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 "purewhite42/HAR_CoPA_Cycle2" \
    --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": "purewhite42/HAR_CoPA_Cycle2",
		"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 "purewhite42/HAR_CoPA_Cycle2" \
        --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": "purewhite42/HAR_CoPA_Cycle2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use purewhite42/HAR_CoPA_Cycle2 with Docker Model Runner:
```
docker model run hf.co/purewhite42/HAR_CoPA_Cycle2
```

purewhite42 commited on Oct 28, 2025

Commit

76bf088

verified ·

1 Parent(s): 99dc824

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -37,7 +37,7 @@ Please refer to the [📺GitHub repo](https://github.com/Purewhite2019/har_copa_
 ## 📈 Performance
 | Cycle |    Method   |  FormalMath500 |             | MiniF2F-Solving |             |
 |:-----:|:-----------:|:--------------:|:-----------:|:---------------:|:-----------:|
-|       |             | Solved         | Budget      | Solved          | Budget      |
 | 1     | BFS         | 9.52% ± 0.57%  | 28139 ± 104 | 9.64% ± 1.66%   | 27712 ± 339 |
 | 1     | WG          | 18.78% ± 0.22% | 18456 ± 92  | 24.95% ± 1.09%  | 18853 ± 454 |
 | 1     | WG $(K_W=16)$   | 21.78% ± 0.12% | 35391 ± 153 | 28.83% ± 0.77%  | 35895 ± 487 |

 ## 📈 Performance
 | Cycle |    Method   |  FormalMath500 |             | MiniF2F-Solving |             |
 |:-----:|:-----------:|:--------------:|:-----------:|:---------------:|:-----------:|
+|       |             | Solved% ↑      | Budget ↓    | Solved % ↑      | Budget ↓    |
 | 1     | BFS         | 9.52% ± 0.57%  | 28139 ± 104 | 9.64% ± 1.66%   | 27712 ± 339 |
 | 1     | WG          | 18.78% ± 0.22% | 18456 ± 92  | 24.95% ± 1.09%  | 18853 ± 454 |
 | 1     | WG $(K_W=16)$   | 21.78% ± 0.12% | 35391 ± 153 | 28.83% ± 0.77%  | 35895 ± 487 |