Instructions to use FreedomIntelligence/phoenix-inst-chat-7b-int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FreedomIntelligence/phoenix-inst-chat-7b-int4 with Transformers:

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

pipe = pipeline("text-generation", model="FreedomIntelligence/phoenix-inst-chat-7b-int4")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FreedomIntelligence/phoenix-inst-chat-7b-int4")
model = AutoModelForCausalLM.from_pretrained("FreedomIntelligence/phoenix-inst-chat-7b-int4")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use FreedomIntelligence/phoenix-inst-chat-7b-int4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FreedomIntelligence/phoenix-inst-chat-7b-int4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FreedomIntelligence/phoenix-inst-chat-7b-int4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/FreedomIntelligence/phoenix-inst-chat-7b-int4

SGLang

How to use FreedomIntelligence/phoenix-inst-chat-7b-int4 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/phoenix-inst-chat-7b-int4" \
    --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/phoenix-inst-chat-7b-int4",
		"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/phoenix-inst-chat-7b-int4" \
        --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/phoenix-inst-chat-7b-int4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use FreedomIntelligence/phoenix-inst-chat-7b-int4 with Docker Model Runner:
```
docker model run hf.co/FreedomIntelligence/phoenix-inst-chat-7b-int4
```

Would you plan to integrate this model with textgen webui?

by Yhyu13 - opened May 4, 2023

Discussion

Yhyu13

May 4, 2023

Hi, I am impressed by multi-lingual abilities which cover smaller countries/nations very well. This can really help the world in better using LLM technology.

I am a textgen webui user, but I am not a coder
I knew that textgen had not supported Bloom models derivatives yet, would you like pull request which features this model which will eventually add Bloom models to textgen's table?

Thanks!

GeneZC

May 5, 2023

We are planning to do so, please stay tuned.

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