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
```

chencyudel commited on Jan 16, 2024

Commit

a3cf15b

verified ·

1 Parent(s): 3d5d811

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -6

README.md CHANGED Viewed

@@ -76,9 +76,6 @@ CodeFuse-Mixtral-8x7B is a Code-LLM finetuned by QLoRA on multiple code-related
-### NLP
-![NLP Performance Radar](codefuse-deepseek-33b-nlp.png)
 <br>
@@ -223,9 +220,9 @@ CodeFuse-DeepSeek-33B 是一个通过QLoRA对基座模型DeepSeek-Coder-33B进
 🔥🔥🔥 2023-09-27开源了CodeFuse-StarCoder-15B模型，在HumanEval pass@1(greedy decoding)上可以达到54.9%, 比StarCoder提高了21%的代码能力（HumanEval）
-🔥🔥🔥 2023-09-26 [CodeFuse-CodeLlama-34B 4bits](https://modelscope.cn/models/codefuse-ai/CodeFuse-CodeLlama-34B-4bits/summary)量化版本发布，量化后模型在HumanEval pass@1指标为73.8% (贪婪解码)。
-🔥🔥🔥 2023-09-11 [CodeFuse-CodeLlama-34B](https://modelscope.cn/models/codefuse-ai/CodeFuse-CodeLlama-34B/summary)发布，HumanEval pass@1指标达到74.4% (贪婪解码), 为当前开源SOTA。
 <br>
@@ -234,7 +231,6 @@ CodeFuse-DeepSeek-33B 是一个通过QLoRA对基座模型DeepSeek-Coder-33B进
 + 如果您想自己微调该模型，可以访问 ✨[MFTCoder](https://github.com/codefuse-ai/MFTCoder)✨✨
-+ 如果您想自己部署该模型，可以访问 ✨[FasterTransformer4CodeFuse](https://github.com/codefuse-ai/FasterTransformer4CodeFuse)✨✨
 + 如果您想观看该模型示例，可以访问 ✨[CodeFuse Demo](https://github.com/codefuse-ai/codefuse)✨✨

 <br>
 🔥🔥🔥 2023-09-27开源了CodeFuse-StarCoder-15B模型，在HumanEval pass@1(greedy decoding)上可以达到54.9%, 比StarCoder提高了21%的代码能力（HumanEval）
+🔥🔥🔥 2023-09-26 CodeFuse-CodeLlama-34B-4bits 量化版本发布，量化后模型在HumanEval pass@1指标为73.8% (贪婪解码)。
+🔥🔥🔥 2023-09-11 CodeFuse-CodeLlama-34B 发布，HumanEval pass@1指标达到74.4% (贪婪解码), 为当前开源SOTA。
 <br>
 + 如果您想自己微调该模型，可以访问 ✨[MFTCoder](https://github.com/codefuse-ai/MFTCoder)✨✨
 + 如果您想观看该模型示例，可以访问 ✨[CodeFuse Demo](https://github.com/codefuse-ai/codefuse)✨✨