Instructions to use NousResearch/Nous-Capybara-7B-V1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NousResearch/Nous-Capybara-7B-V1 with Transformers:

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

pipe = pipeline("text-generation", model="NousResearch/Nous-Capybara-7B-V1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NousResearch/Nous-Capybara-7B-V1")
model = AutoModelForCausalLM.from_pretrained("NousResearch/Nous-Capybara-7B-V1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NousResearch/Nous-Capybara-7B-V1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NousResearch/Nous-Capybara-7B-V1"
# 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-7B-V1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/NousResearch/Nous-Capybara-7B-V1

SGLang

How to use NousResearch/Nous-Capybara-7B-V1 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-7B-V1" \
    --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-7B-V1",
		"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-7B-V1" \
        --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-7B-V1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use NousResearch/Nous-Capybara-7B-V1 with Docker Model Runner:
```
docker model run hf.co/NousResearch/Nous-Capybara-7B-V1
```

LDJnr commited on Sep 26, 2023

Commit

7facad3

1 Parent(s): 8bcb6f1

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -9

README.md CHANGED Viewed

@@ -68,14 +68,6 @@ ASSISTANT:
 ![Capybara](https://img001.prntscr.com/file/img001/85X3L9ZxTsOKo3fUQ7GRVA.png)
-## When should I use Capybara or Hermes 2?
-- Hermes 2 is trained on purely single turn instruction examples.
-- Capybara is trained mostly on multi-turn, long context, highly curated and cleaned GPT-4 conversations with real humans.
-For these reasons, it's reccomended to give Capybara a try if you want to have multi-turn conversations and/or long context communication.
 ## Benchmarks! (Important to note that all mentioned benchmarks are single-turn and don't test multi-turn capabilities, Capybara should excel even further at multi-turn conversational tasks.)
 ![Capybara](https://i.imgur.com/n8lkmyK.png)
@@ -115,4 +107,3 @@ The following are benchmarks we checked for contamination for:
 - MMLU
 - GPT4All

 ![Capybara](https://img001.prntscr.com/file/img001/85X3L9ZxTsOKo3fUQ7GRVA.png)
 ## Benchmarks! (Important to note that all mentioned benchmarks are single-turn and don't test multi-turn capabilities, Capybara should excel even further at multi-turn conversational tasks.)
 ![Capybara](https://i.imgur.com/n8lkmyK.png)
 - MMLU
 - GPT4All