Instructions to use codefuse-ai/CodeFuse-Mixtral-8x7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use codefuse-ai/CodeFuse-Mixtral-8x7B with Transformers:

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

pipe = pipeline("text-generation", model="codefuse-ai/CodeFuse-Mixtral-8x7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("codefuse-ai/CodeFuse-Mixtral-8x7B")
model = AutoModelForCausalLM.from_pretrained("codefuse-ai/CodeFuse-Mixtral-8x7B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use codefuse-ai/CodeFuse-Mixtral-8x7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "codefuse-ai/CodeFuse-Mixtral-8x7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "codefuse-ai/CodeFuse-Mixtral-8x7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/codefuse-ai/CodeFuse-Mixtral-8x7B

SGLang

How to use codefuse-ai/CodeFuse-Mixtral-8x7B 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/CodeFuse-Mixtral-8x7B" \
    --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": "codefuse-ai/CodeFuse-Mixtral-8x7B",
		"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 "codefuse-ai/CodeFuse-Mixtral-8x7B" \
        --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": "codefuse-ai/CodeFuse-Mixtral-8x7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use codefuse-ai/CodeFuse-Mixtral-8x7B with Docker Model Runner:
```
docker model run hf.co/codefuse-ai/CodeFuse-Mixtral-8x7B
```

codefuse-admin commited on Jan 19, 2024

Commit

da12104

verified ·

1 Parent(s): a3cf15b

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -212,6 +212,8 @@ CodeFuse-DeepSeek-33B 是一个通过QLoRA对基座模型DeepSeek-Coder-33B进
 🔥🔥🔥 2024-01-12 CodeFuse-DeepSeek-33B模型发布，模型在HumanEval pass@1指标为78.65% (贪婪解码)。
 🔥🔥🔥 2023-11-10 开源了CodeFuse-CodeGeeX2-6B模型，在HumanEval pass@1(greedy decoding)上可以达到48.12%, 比CodeGeeX2提高了9.22%的代码能力（HumanEval）
 🔥🔥🔥 2023-10-20 公布了CodeFuse-QWen-14B技术文档，感兴趣详见微信公众号CodeFuse文章：https://mp.weixin.qq.com/s/PCQPkvbvfxSPzsqjOILCDw

 🔥🔥🔥 2024-01-12 CodeFuse-DeepSeek-33B模型发布，模型在HumanEval pass@1指标为78.65% (贪婪解码)。
+🔥🔥🔥 2024-01-12 CodeFuse-Mixtral-8x7B模型发布，模型在HumanEval pass@1指标为56.1% (贪婪解码)。微信公众号文章：https://mp.weixin.qq.com/s/xI3f0iUKq9TIIKZ_kMtcQg
 🔥🔥🔥 2023-11-10 开源了CodeFuse-CodeGeeX2-6B模型，在HumanEval pass@1(greedy decoding)上可以达到48.12%, 比CodeGeeX2提高了9.22%的代码能力（HumanEval）
 🔥🔥🔥 2023-10-20 公布了CodeFuse-QWen-14B技术文档，感兴趣详见微信公众号CodeFuse文章：https://mp.weixin.qq.com/s/PCQPkvbvfxSPzsqjOILCDw