Instructions to use Intel/neural-chat-7b-v3-3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Intel/neural-chat-7b-v3-3 with Transformers:

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

pipe = pipeline("text-generation", model="Intel/neural-chat-7b-v3-3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Intel/neural-chat-7b-v3-3")
model = AutoModelForCausalLM.from_pretrained("Intel/neural-chat-7b-v3-3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Intel/neural-chat-7b-v3-3 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-v3-3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Intel/neural-chat-7b-v3-3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Intel/neural-chat-7b-v3-3

SGLang

How to use Intel/neural-chat-7b-v3-3 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-v3-3" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Intel/neural-chat-7b-v3-3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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-v3-3" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Intel/neural-chat-7b-v3-3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Intel/neural-chat-7b-v3-3 with Docker Model Runner:
```
docker model run hf.co/Intel/neural-chat-7b-v3-3
```

Interesting phenomenon in response

by Metricon - opened Feb 25, 2024

Discussion

Metricon

Feb 25, 2024

This model is one of the best available at this size, but there is an interesting phenomenon that appeared at random: If the prompt is set to "How much gold is in the universe?" with "do_sample": False running at float16, the output will generate the following response and then never complete as the model will continue to use high GPU usage as though it's stuck in an infinite loop:

The exact amount of gold in the universe is difficult to determine, but estimates suggest that there is a significant amount of it. Gold is a relatively rare element, making up only about

No other query appears to do this, including just replacing the word "gold" with "silver" or "iron" or replacing "universe" with "world".

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