Instructions to use Mathoctopus/Parallel_xRFT_7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mathoctopus/Parallel_xRFT_7B with Transformers:

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

pipe = pipeline("text-generation", model="Mathoctopus/Parallel_xRFT_7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Mathoctopus/Parallel_xRFT_7B")
model = AutoModelForCausalLM.from_pretrained("Mathoctopus/Parallel_xRFT_7B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Mathoctopus/Parallel_xRFT_7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mathoctopus/Parallel_xRFT_7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mathoctopus/Parallel_xRFT_7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Mathoctopus/Parallel_xRFT_7B

SGLang

How to use Mathoctopus/Parallel_xRFT_7B 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 "Mathoctopus/Parallel_xRFT_7B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mathoctopus/Parallel_xRFT_7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Mathoctopus/Parallel_xRFT_7B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mathoctopus/Parallel_xRFT_7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Mathoctopus/Parallel_xRFT_7B with Docker Model Runner:
```
docker model run hf.co/Mathoctopus/Parallel_xRFT_7B
```

Parallel_xRFT_7B

Commit History

Update README.md

e24b4ec

Nuo97 commited on Dec 31, 2023

Update README.md

5a31e2d

compasszzn commited on Nov 2, 2023

Update README.md

57ec1c1

compasszzn commited on Oct 22, 2023

Update README.md

0dfee9b

compasszzn commited on Oct 21, 2023