Instructions to use tomhu/RL4TG-DeepSeek-Coder-1.3B-Coder6.7B-Offline-SFT-GRPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tomhu/RL4TG-DeepSeek-Coder-1.3B-Coder6.7B-Offline-SFT-GRPO with Transformers:

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

pipe = pipeline("text-generation", model="tomhu/RL4TG-DeepSeek-Coder-1.3B-Coder6.7B-Offline-SFT-GRPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tomhu/RL4TG-DeepSeek-Coder-1.3B-Coder6.7B-Offline-SFT-GRPO")
model = AutoModelForCausalLM.from_pretrained("tomhu/RL4TG-DeepSeek-Coder-1.3B-Coder6.7B-Offline-SFT-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 tomhu/RL4TG-DeepSeek-Coder-1.3B-Coder6.7B-Offline-SFT-GRPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tomhu/RL4TG-DeepSeek-Coder-1.3B-Coder6.7B-Offline-SFT-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": "tomhu/RL4TG-DeepSeek-Coder-1.3B-Coder6.7B-Offline-SFT-GRPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tomhu/RL4TG-DeepSeek-Coder-1.3B-Coder6.7B-Offline-SFT-GRPO

SGLang

How to use tomhu/RL4TG-DeepSeek-Coder-1.3B-Coder6.7B-Offline-SFT-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 "tomhu/RL4TG-DeepSeek-Coder-1.3B-Coder6.7B-Offline-SFT-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": "tomhu/RL4TG-DeepSeek-Coder-1.3B-Coder6.7B-Offline-SFT-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 "tomhu/RL4TG-DeepSeek-Coder-1.3B-Coder6.7B-Offline-SFT-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": "tomhu/RL4TG-DeepSeek-Coder-1.3B-Coder6.7B-Offline-SFT-GRPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tomhu/RL4TG-DeepSeek-Coder-1.3B-Coder6.7B-Offline-SFT-GRPO with Docker Model Runner:
```
docker model run hf.co/tomhu/RL4TG-DeepSeek-Coder-1.3B-Coder6.7B-Offline-SFT-GRPO
```

DeepSeek-Coder-1.3B Coder6.7B Offline SFT + GRPO

Unfiltered offline SFT from DeepSeek-Coder-6.7B teacher generations followed by two-epoch GRPO.

Checkpoint revisions: checkpoint-10, checkpoint-20, checkpoint-30, checkpoint-40, checkpoint-50, checkpoint-60, checkpoint-70, checkpoint-80, checkpoint-90, checkpoint-98.

This model is part of the RL4TG experimental model collection.