Instructions to use codefuse-ai/CodeFuse-DeepSeek-33B-4bits with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use codefuse-ai/CodeFuse-DeepSeek-33B-4bits with Transformers:

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

pipe = pipeline("text-generation", model="codefuse-ai/CodeFuse-DeepSeek-33B-4bits")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("codefuse-ai/CodeFuse-DeepSeek-33B-4bits")
model = AutoModelForCausalLM.from_pretrained("codefuse-ai/CodeFuse-DeepSeek-33B-4bits")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use codefuse-ai/CodeFuse-DeepSeek-33B-4bits with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "codefuse-ai/CodeFuse-DeepSeek-33B-4bits"
# 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-DeepSeek-33B-4bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/codefuse-ai/CodeFuse-DeepSeek-33B-4bits

SGLang

How to use codefuse-ai/CodeFuse-DeepSeek-33B-4bits 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-DeepSeek-33B-4bits" \
    --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-DeepSeek-33B-4bits",
		"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-DeepSeek-33B-4bits" \
        --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-DeepSeek-33B-4bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use codefuse-ai/CodeFuse-DeepSeek-33B-4bits with Docker Model Runner:
```
docker model run hf.co/codefuse-ai/CodeFuse-DeepSeek-33B-4bits
```

codefuse-admin commited on Jan 12, 2024

Commit

7825fb5

verified ·

1 Parent(s): 8661fb7

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -14,7 +14,7 @@ tasks:
 ## Model Description
-CodeFuse-DeepSeek-33B-4bits is the 4-bit quantized version of [CodeFuse-DeepSeek-33B](https://modelscope.cn/models/codefuse-ai/CodeFuse-DeepSeek-33B/summary) which is a 33B Code-LLM finetuned by QLoRA on multiple code-related tasks on the base model DeepSeek-Coder-33B.
 After undergoing 4-bit quantization, the CodeFuse-DeepSeek-33B-4bits model can be loaded on either a single A10 (24GB VRAM) or an RTX 4090 (24GB VRAM). Moreover, the quantized model still achives an impressive accuracy of 78.05% on the Humaneval pass@1 metric.
@@ -34,9 +34,9 @@ After undergoing 4-bit quantization, the CodeFuse-DeepSeek-33B-4bits model can b
   🔥🔥 2023-09-27 CodeFuse-StarCoder-15B has been released, achieving a pass@1 (greedy decoding) score of 54.9% on HumanEval, which is a 21% increase compared to StarCoder's 33.6%.
-🔥🔥🔥 2023-09-26 We are pleased to announce the release of the [4-bit quantized version](https://modelscope.cn/models/codefuse-ai/CodeFuse-CodeLlama-34B-4bits/summary) of [CodeFuse-CodeLlama-34B](https://modelscope.cn/models/codefuse-ai/CodeFuse-CodeLlama-34B/summary). Despite the quantization process, the model still achieves a remarkable 73.8% accuracy (greedy decoding) on the HumanEval pass@1 metric.
-🔥🔥🔥 2023-09-11 [CodeFuse-CodeLlama34B](https://modelscope.cn/models/codefuse-ai/CodeFuse-CodeLlama-34B/summary) has achieved 74.4% of pass@1 (greedy decoding) on HumanEval, which is SOTA results for openspurced LLMs at present.
 <br>
@@ -209,7 +209,7 @@ if __name__ == "__main__":
 ## 模型简介
-CodeFuse-DeepSeek-33B-4bits是代码大模型[CodeFuse-DeepSeek-33B](https://modelscope.cn/models/codefuse-ai/CodeFuse-DeepSeek-33B/summary)的4-bits量化版本，后者基于底座模型DeepSeek-Coder-33B使用MFTCoder框架在多个代码相关任务上微调得到。
 经过4-bits量化后，CodeFuse-DeepSeek-33B-4bits可在单张A10 (24GB显存)或者RTX 4090（24G显存）上加载。量化后，CodeFuse-DeepSeek-33B-4bits仍取得HumanEval pass@1 78.05%。
 <br>
@@ -228,9 +228,9 @@ CodeFuse-DeepSeek-33B-4bits是代码大模型[CodeFuse-DeepSeek-33B](https://mod
   🔥🔥 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>

 ## Model Description
+CodeFuse-DeepSeek-33B-4bits is the 4-bit quantized version of [CodeFuse-DeepSeek-33B](https://huggingface.co/codefuse-ai/CodeFuse-DeepSeek-33B) which is a 33B Code-LLM finetuned by QLoRA on multiple code-related tasks on the base model DeepSeek-Coder-33B.
 After undergoing 4-bit quantization, the CodeFuse-DeepSeek-33B-4bits model can be loaded on either a single A10 (24GB VRAM) or an RTX 4090 (24GB VRAM). Moreover, the quantized model still achives an impressive accuracy of 78.05% on the Humaneval pass@1 metric.
   🔥🔥 2023-09-27 CodeFuse-StarCoder-15B has been released, achieving a pass@1 (greedy decoding) score of 54.9% on HumanEval, which is a 21% increase compared to StarCoder's 33.6%.
+🔥🔥🔥 2023-09-26 We are pleased to announce the release of the [4-bit quantized version](https://huggingface.co/codefuse-ai/CodeFuse-CodeLlama-34B-4bits) of [CodeFuse-CodeLlama-34B](https://modelscope.cn/models/codefuse-ai/CodeFuse-CodeLlama-34B/summary). Despite the quantization process, the model still achieves a remarkable 73.8% accuracy (greedy decoding) on the HumanEval pass@1 metric.
+🔥🔥🔥 2023-09-11 [CodeFuse-CodeLlama34B](https://huggingface.co/codefuse-ai/CodeFuse-CodeLlama-34B-4bits) has achieved 74.4% of pass@1 (greedy decoding) on HumanEval, which is SOTA results for openspurced LLMs at present.
 <br>
 ## 模型简介
+CodeFuse-DeepSeek-33B-4bits是代码大模型[CodeFuse-DeepSeek-33B](https://huggingface.co/codefuse-ai/CodeFuse-DeepSeek-33B)的4-bits量化版本，后者基于底座模型DeepSeek-Coder-33B使用MFTCoder框架在多个代码相关任务上微调得到。
 经过4-bits量化后，CodeFuse-DeepSeek-33B-4bits可在单张A10 (24GB显存)或者RTX 4090（24G显存）上加载。量化后，CodeFuse-DeepSeek-33B-4bits仍取得HumanEval pass@1 78.05%。
 <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](https://huggingface.co/codefuse-ai/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](https://huggingface.co/codefuse-ai/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>