Instructions to use FreedomIntelligence/AceGPT-7B-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FreedomIntelligence/AceGPT-7B-chat with Transformers:

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

pipe = pipeline("text-generation", model="FreedomIntelligence/AceGPT-7B-chat")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FreedomIntelligence/AceGPT-7B-chat")
model = AutoModelForCausalLM.from_pretrained("FreedomIntelligence/AceGPT-7B-chat", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FreedomIntelligence/AceGPT-7B-chat with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/FreedomIntelligence/AceGPT-7B-chat

SGLang

How to use FreedomIntelligence/AceGPT-7B-chat 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 "FreedomIntelligence/AceGPT-7B-chat" \
    --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": "FreedomIntelligence/AceGPT-7B-chat",
		"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 "FreedomIntelligence/AceGPT-7B-chat" \
        --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": "FreedomIntelligence/AceGPT-7B-chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use FreedomIntelligence/AceGPT-7B-chat with Docker Model Runner:
```
docker model run hf.co/FreedomIntelligence/AceGPT-7B-chat
```

Prompt Template?

by amgadhasan - opened Jan 1, 2024

Discussion

amgadhasan

Jan 1, 2024

What's the prompt template for this model?

Is it similar to llama2-chat? Or does it use chatml?

jianqing666

Jan 2, 2024

Hello,

Thank you for your inquiry! Regarding your question, you can find the prompt template used by AceGPT in the web_demo.py file in our GitHub repository. For detailed information about the prompt template, please check the following link:https://github.com/FreedomIntelligence/AceGPT/blob/main/web_demo.py.

If you have any further questions or need additional assistance, feel free to let us know.

Thank you!

hh2017

Jan 2, 2024

You can find it in our github.

jianqing666

Jan 2, 2024

Hello,

Thank you for your inquiry! Regarding your question, you can find the prompt template used by AceGPT in the web_demo.py file in our GitHub repository. For detailed information about the prompt template, please check the following link:https://github.com/FreedomIntelligence/AceGPT/blob/main/web_demo.py.

If you have any further questions or need additional assistance, feel free to let us know.

Thank you!

jianqing666 changed discussion status to closed Jan 2, 2024

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