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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Install from pip and serve model

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

Use Docker

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

SGLang

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

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

License

#10

by mrfakename - opened Nov 17, 2023

Discussion

mrfakename

Nov 17, 2023

Does this have the restrictions of the Yi license (NC) since it’s a fine tune?

mishaml77

Jan 13, 2024

Any update on this??

teknium

NousResearch org Jan 15, 2024

It is MIT license

mrfakename

Jan 15, 2024

Nice, so we can use it commercially? The Yi license doesn’t apply?

MaziyarPanahi

Jan 16, 2024

The Capybara series is the first Nous collection of models made by fine-tuning mostly on data created by Nous in-house.

  "_name_or_path": "larryvrh/Yi-34B-200K-Llamafied",

I am not a lawyer, but I am pretty sure you cannot just fine-tune a model and set a different license than the base model. (That's why everyone always says Llama-2 license instead of Apache 2.0 or MIT). Don't get me wrong, would love to try Yi in commercial projects! :p

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