Instructions to use Salesforce/codegen25-7b-multi_P with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Salesforce/codegen25-7b-multi_P with Transformers:

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

pipe = pipeline("text-generation", model="Salesforce/codegen25-7b-multi_P")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Salesforce/codegen25-7b-multi_P")
model = AutoModelForCausalLM.from_pretrained("Salesforce/codegen25-7b-multi_P")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Salesforce/codegen25-7b-multi_P with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Salesforce/codegen25-7b-multi_P"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Salesforce/codegen25-7b-multi_P",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Salesforce/codegen25-7b-multi_P

SGLang

How to use Salesforce/codegen25-7b-multi_P 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 "Salesforce/codegen25-7b-multi_P" \
    --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": "Salesforce/codegen25-7b-multi_P",
		"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 "Salesforce/codegen25-7b-multi_P" \
        --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": "Salesforce/codegen25-7b-multi_P",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Salesforce/codegen25-7b-multi_P with Docker Model Runner:
```
docker model run hf.co/Salesforce/codegen25-7b-multi_P
```

script to ggml quantize this model?

by MichelNivard - opened Jul 26, 2023

Discussion

MichelNivard

Jul 26, 2023

Anyone have a script for quantizing this model for use with llama.cpp (so GGML format)?

hackdefendr

Dec 25, 2023

I came here today (Christmas Day) looking for the same thing. The current llama.cpp convert scripts do not work.
Since you posted this in July and no one else has replied, I'm guessing it won't or can't be converted.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment