Instructions to use Intel/neural-chat-7b-v3-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Intel/neural-chat-7b-v3-2 with Transformers:

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

pipe = pipeline("text-generation", model="Intel/neural-chat-7b-v3-2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Intel/neural-chat-7b-v3-2")
model = AutoModelForCausalLM.from_pretrained("Intel/neural-chat-7b-v3-2")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Intel/neural-chat-7b-v3-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Intel/neural-chat-7b-v3-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Intel/neural-chat-7b-v3-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Intel/neural-chat-7b-v3-2

SGLang

How to use Intel/neural-chat-7b-v3-2 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 "Intel/neural-chat-7b-v3-2" \
    --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": "Intel/neural-chat-7b-v3-2",
		"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 "Intel/neural-chat-7b-v3-2" \
        --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": "Intel/neural-chat-7b-v3-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Intel/neural-chat-7b-v3-2 with Docker Model Runner:
```
docker model run hf.co/Intel/neural-chat-7b-v3-2
```

v3-2 vs v3-1

by bartowski - opened Dec 2, 2023

Discussion

bartowski

Dec 2, 2023

Not much in the model card, any notable differences? increased training or otherwise?

userBo

Dec 3, 2023

@lvkaokao

PoVRAZOR

Dec 3, 2023

In my initial testing, v3.2 is getting facts more correct than v3.1, but I have been using the 5bit quantized models. I'm currently downloading the fp16 version for further testing.

Metricon

Dec 7, 2023

•

edited Dec 7, 2023

In testing, this new version appears to work very well.

iskenderulgen

Dec 7, 2023

Is the model trained with Quantization Aware Training to save more accuracy do we have any knowledge of that ? and the model checkpoints in the files are full precision or half precision ? Apart from the questions model gives great results for language understanding thought in some cases gives better results when using 8bit inference over torch fp16 dtype need more testing probably

lvkaokao

Intel org Dec 11, 2023

@bartowski hi, we update the model card

@PoVRAZOR Thanks for your testing, we continue training the https://huggingface.co/Intel/neural-chat-7b-v3-1 with https://huggingface.co/datasets/meta-math/MetaMathQA dataset

@Metricon Thanks~

@iskenderulgen hi, we use fp16 mixed training.

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