Instructions to use TheBloke/zephyr-7B-beta-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/zephyr-7B-beta-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/zephyr-7B-beta-AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/zephyr-7B-beta-AWQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/zephyr-7B-beta-AWQ")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheBloke/zephyr-7B-beta-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/zephyr-7B-beta-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/zephyr-7B-beta-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TheBloke/zephyr-7B-beta-AWQ

SGLang

How to use TheBloke/zephyr-7B-beta-AWQ 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 "TheBloke/zephyr-7B-beta-AWQ" \
    --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": "TheBloke/zephyr-7B-beta-AWQ",
		"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 "TheBloke/zephyr-7B-beta-AWQ" \
        --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": "TheBloke/zephyr-7B-beta-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TheBloke/zephyr-7B-beta-AWQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/zephyr-7B-beta-AWQ
```

vLLM out of memory

by cfrancois7 - opened Nov 21, 2023

Discussion

cfrancois7

Nov 21, 2023

•

edited Nov 21, 2023

I have only a RTX 3070 with 8Go VRAM.

When I execute your code for AutoAWQ, it works well on my computer.
I succeed to manage the size of my max tokens.
I run with around 7Go of RAM.

But when I want to test vLLM, the script want 14Go of GPU RAM allocation, and crash.
I do not succeed to change the max tokens size.

willowill5

Dec 4, 2023

•

edited Dec 4, 2023

Try with --max-model-len 512

cfrancois7

Dec 8, 2023

I reinstall and test with :

llm = LLM(
    model="TheBloke/zephyr-7B-beta-AWQ", 
    quantization="awq",
    dtype="auto",
    max_model_len=512,
   gpu_memory_utilization=0.8
)

And it works.

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