Instructions to use Nitral-Archive/Kunocchini-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nitral-Archive/Kunocchini-7b with Transformers:

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

pipe = pipeline("text-generation", model="Nitral-Archive/Kunocchini-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Nitral-Archive/Kunocchini-7b")
model = AutoModelForCausalLM.from_pretrained("Nitral-Archive/Kunocchini-7b")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Nitral-Archive/Kunocchini-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Nitral-Archive/Kunocchini-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nitral-Archive/Kunocchini-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Nitral-Archive/Kunocchini-7b

SGLang

How to use Nitral-Archive/Kunocchini-7b 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 "Nitral-Archive/Kunocchini-7b" \
    --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": "Nitral-Archive/Kunocchini-7b",
		"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 "Nitral-Archive/Kunocchini-7b" \
        --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": "Nitral-Archive/Kunocchini-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Nitral-Archive/Kunocchini-7b with Docker Model Runner:
```
docker model run hf.co/Nitral-Archive/Kunocchini-7b
```

Kunocchini-7b

Commit History

Adding Evaluation Results (#1)

412fb99
verified

Nitral

leaderboard-pr-bot commited on Mar 4, 2024

Upload 2 files

5238e6d
verified

Nitral commited on Feb 19, 2024

Delete ST TextGen Preset/Nitral's Smooth Brain Sampling.json

6d16707
verified

Nitral commited on Feb 19, 2024

Update README.md

dd1e7af
verified

Nitral commited on Feb 15, 2024

Update README.md

4369460
verified

Nitral commited on Feb 15, 2024

Update README.md

391edf7
verified

Nitral commited on Feb 15, 2024

Update README.md

a8bf199
verified

Nitral commited on Feb 14, 2024

Update README.md

c0511e5
verified

Nitral commited on Feb 9, 2024

Update README.md

8450940
verified

Nitral commited on Feb 7, 2024