Instructions to use codefuse-ai/CodeFuse-CodeLlama-34B-4bits with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use codefuse-ai/CodeFuse-CodeLlama-34B-4bits with Transformers:

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

pipe = pipeline("text-generation", model="codefuse-ai/CodeFuse-CodeLlama-34B-4bits")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("codefuse-ai/CodeFuse-CodeLlama-34B-4bits")
model = AutoModelForCausalLM.from_pretrained("codefuse-ai/CodeFuse-CodeLlama-34B-4bits")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use codefuse-ai/CodeFuse-CodeLlama-34B-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-CodeLlama-34B-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-CodeLlama-34B-4bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/codefuse-ai/CodeFuse-CodeLlama-34B-4bits

SGLang

How to use codefuse-ai/CodeFuse-CodeLlama-34B-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-CodeLlama-34B-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-CodeLlama-34B-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-CodeLlama-34B-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-CodeLlama-34B-4bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use codefuse-ai/CodeFuse-CodeLlama-34B-4bits with Docker Model Runner:
```
docker model run hf.co/codefuse-ai/CodeFuse-CodeLlama-34B-4bits
```

Update README.md

by goforce5500 - opened Oct 12, 2023

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

-2

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -136,7 +136,7 @@ def load_model_tokenizer(model_name_or_local_path):
     tokenizer = AutoTokenizer.from_pretrained(model_name_or_local_path,
                                               trust_remote_code=True,
                                               use_fast=False,
-                                              lagecy=False)
     tokenizer.padding_side = "left"
     model = AutoGPTQForCausalLM.from_quantized(model_name_or_local_path,
@@ -328,7 +328,7 @@ def load_model_tokenizer(model_name_or_local_path):
     tokenizer = AutoTokenizer.from_pretrained(model_name_or_local_path,
                                               trust_remote_code=True,
                                               use_fast=False,
-                                              lagecy=False)
     tokenizer.padding_side = "left"
     model = AutoGPTQForCausalLM.from_quantized(model_name_or_local_path,

     tokenizer = AutoTokenizer.from_pretrained(model_name_or_local_path,
                                               trust_remote_code=True,
                                               use_fast=False,
+                                              legacy=False)
     tokenizer.padding_side = "left"
     model = AutoGPTQForCausalLM.from_quantized(model_name_or_local_path,
     tokenizer = AutoTokenizer.from_pretrained(model_name_or_local_path,
                                               trust_remote_code=True,
                                               use_fast=False,
+                                              legacy=False)
     tokenizer.padding_side = "left"
     model = AutoGPTQForCausalLM.from_quantized(model_name_or_local_path,