Instructions to use INC4AI/neural-chat-7b-v3-1-int4-inc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use INC4AI/neural-chat-7b-v3-1-int4-inc with Transformers:

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

pipe = pipeline("text-generation", model="INC4AI/neural-chat-7b-v3-1-int4-inc")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("INC4AI/neural-chat-7b-v3-1-int4-inc")
model = AutoModelForCausalLM.from_pretrained("INC4AI/neural-chat-7b-v3-1-int4-inc", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use INC4AI/neural-chat-7b-v3-1-int4-inc with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "INC4AI/neural-chat-7b-v3-1-int4-inc"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "INC4AI/neural-chat-7b-v3-1-int4-inc",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/INC4AI/neural-chat-7b-v3-1-int4-inc

SGLang

How to use INC4AI/neural-chat-7b-v3-1-int4-inc 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 "INC4AI/neural-chat-7b-v3-1-int4-inc" \
    --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": "INC4AI/neural-chat-7b-v3-1-int4-inc",
		"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 "INC4AI/neural-chat-7b-v3-1-int4-inc" \
        --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": "INC4AI/neural-chat-7b-v3-1-int4-inc",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use INC4AI/neural-chat-7b-v3-1-int4-inc with Docker Model Runner:
```
docker model run hf.co/INC4AI/neural-chat-7b-v3-1-int4-inc
```

neural-chat-7b-v3-1-int4-inc

Commit History

Update README.md

e27c27b
verified

weiweiz1 commited on Aug 26, 2024

Update README.md

3320708
verified

yintongl commited on May 31, 2024

Update README.md

0e125f8
verified

yintongl commited on May 31, 2024

Update README.md

c78075e
verified

yintongl commited on May 31, 2024

update script following enable_quanted_input argument change

ccd1a6a
verified

yintongl commited on Apr 28, 2024

Update README.md

46cab48
verified

wenhuach commited on Mar 13, 2024

Update README.md

bc08ce7
verified

wenhuach commited on Mar 13, 2024