Instructions to use sergiopaniego/Qwen3-8B-opencode-deepcoder-grpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sergiopaniego/Qwen3-8B-opencode-deepcoder-grpo with Transformers:

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

pipe = pipeline("text-generation", model="sergiopaniego/Qwen3-8B-opencode-deepcoder-grpo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sergiopaniego/Qwen3-8B-opencode-deepcoder-grpo")
model = AutoModelForCausalLM.from_pretrained("sergiopaniego/Qwen3-8B-opencode-deepcoder-grpo", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sergiopaniego/Qwen3-8B-opencode-deepcoder-grpo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sergiopaniego/Qwen3-8B-opencode-deepcoder-grpo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sergiopaniego/Qwen3-8B-opencode-deepcoder-grpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sergiopaniego/Qwen3-8B-opencode-deepcoder-grpo

SGLang

How to use sergiopaniego/Qwen3-8B-opencode-deepcoder-grpo 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 "sergiopaniego/Qwen3-8B-opencode-deepcoder-grpo" \
    --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": "sergiopaniego/Qwen3-8B-opencode-deepcoder-grpo",
		"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 "sergiopaniego/Qwen3-8B-opencode-deepcoder-grpo" \
        --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": "sergiopaniego/Qwen3-8B-opencode-deepcoder-grpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sergiopaniego/Qwen3-8B-opencode-deepcoder-grpo with Docker Model Runner:
```
docker model run hf.co/sergiopaniego/Qwen3-8B-opencode-deepcoder-grpo
```

sergiopaniego HF Staff commited on Jul 28

Commit

6c98f90

verified ·

1 Parent(s): 22eedb0

End of training

Browse files

Files changed (2) hide show

README.md +3 -3
model.safetensors +1 -1

README.md CHANGED Viewed

@@ -4,11 +4,11 @@ library_name: transformers
 model_name: Qwen3-8B-opencode-deepcoder-grpo
 tags:
 - generated_from_trainer
-- trl
-- async-grpo
-- trackio:https://huggingface.co/spaces/sergiopaniego/opencode-hf-sandbox-static-cc732a
 - trackio
 - hf_jobs
 licence: license
 ---

 model_name: Qwen3-8B-opencode-deepcoder-grpo
 tags:
 - generated_from_trainer
+- trackio:https://huggingface.co/spaces/sergiopaniego/opencode-hf-sandbox-static-817816
 - trackio
+- trl
 - hf_jobs
+- async-grpo
 licence: license
 ---

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30859d6f98aefe87931af5ac9fc9b865cbae6bde1f1dbae0a2a7a82099a4ff94
 size 32762987816

 version https://git-lfs.github.com/spec/v1
+oid sha256:ad64775084f284a3e63ba7a7336e8f1b7af9f4625d1479c7fb8a05ab8ee28884
 size 32762987816