Instructions to use TheBloke/Nous-Capybara-34B-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/Nous-Capybara-34B-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/Nous-Capybara-34B-AWQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/Nous-Capybara-34B-AWQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/Nous-Capybara-34B-AWQ")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TheBloke/Nous-Capybara-34B-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/Nous-Capybara-34B-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/Nous-Capybara-34B-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/Nous-Capybara-34B-AWQ

SGLang

How to use TheBloke/Nous-Capybara-34B-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/Nous-Capybara-34B-AWQ" \
    --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": "TheBloke/Nous-Capybara-34B-AWQ",
		"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 "TheBloke/Nous-Capybara-34B-AWQ" \
        --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": "TheBloke/Nous-Capybara-34B-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/Nous-Capybara-34B-AWQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/Nous-Capybara-34B-AWQ
```

How much memory does this model require?

by wangdafa - opened Nov 21, 2023

Discussion

wangdafa

Nov 21, 2023

I used two 4090 to run this model and still OOM。

python -m fastchat.serve.vllm_worker --model-path TheBloke/Nous-Capybara-34B-AWQ --trust-remote-code --tensor-parallel-size 2 --quantization awq  --dtype auto

Yhyu13

Nov 21, 2023

You should limit the context length to 8192, otherwise it will try to load 200K context length which roughly need extra 40G vram

wangdafa

Nov 21, 2023

You should limit the context length to 8192, otherwise it will try to load 200K context length which roughly need extra 40G vram

Thank you for your answer. The problem has been resolved

But I met a new problem, that is, vllm seems to not support the template of Nous-Capybara-34B, even if i specify --conv-template manticore. Is this a bug of vllm?

Yhyu13

Nov 21, 2023

@wangdafa

https://github.com/lm-sys/FastChat/blob/e53c73f22efa9a37bf76af8783c96049276a2e98/fastchat/conversation.py#L789

I don't think manticore has system prompt, maybe that was the cause. Try Vicuna or airoboros?

wangdafa changed discussion status to closed Dec 18, 2023

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