Instructions to use Intel/neural-chat-7b-v1-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Intel/neural-chat-7b-v1-1 with Transformers:

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

pipe = pipeline("text-generation", model="Intel/neural-chat-7b-v1-1", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Intel/neural-chat-7b-v1-1", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Intel/neural-chat-7b-v1-1", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Intel/neural-chat-7b-v1-1 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-v1-1"
# 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-v1-1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Intel/neural-chat-7b-v1-1

SGLang

How to use Intel/neural-chat-7b-v1-1 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-v1-1" \
    --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-v1-1",
		"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-v1-1" \
        --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-v1-1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Intel/neural-chat-7b-v1-1 with Docker Model Runner:
```
docker model run hf.co/Intel/neural-chat-7b-v1-1
```

Error load Model

by NickyNicky - opened Dec 9, 2023

Discussion

NickyNicky

Dec 9, 2023

!pip install intel-extension-for-transformers

from transformers import AutoTokenizer, TextStreamer
from intel_extension_for_transformers.transformers import AutoModelForCausalLM
model_name = "Intel/neural-chat-7b-v1-1"     # Hugging Face model_id or local model

prompt = "Once upon a time, there existed a little girl,"

tokenizer = AutoTokenizer.from_pretrained(model_name, 
                                          trust_remote_code=True)
inputs = tokenizer(prompt, return_tensors="pt").input_ids
streamer = TextStreamer(tokenizer)

model = AutoModelForCausalLM.from_pretrained(model_name, 
                                             load_in_8bit=True,
                                             trust_remote_code=True)
outputs = model.generate(inputs, streamer=streamer, max_new_tokens=300)

Error:

!pip install git+"https://github.com/HazyResearch/flash-attention.git#subdirectory=csrc/layer_norm"

BoDong

Intel org Dec 11, 2023

•

edited Dec 11, 2023

Thanks for your usage, but from the log you provided, we found that the error happened in this project https://github.com/togethercomputer/stripedhyena, not related to ours project.

I will recommend you to go through following suggestions to fix the error for "togethercomputer/stripedhyena"
There are two solutions for second pip install error
1. Make sure the env is installed Microsoft Visual C++ Build Tools or MinGW-w64 for windows, GCC and cmake for Linux . Therefore the build process for flash-attention may successfully.
2. Install flash-attention through pre build binary rather than build in time

After solve second error and successfully install flash-attention, the first import module error should be solved at same time.

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