Instructions to use alexandreteles/bonito-v1-awq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alexandreteles/bonito-v1-awq with Transformers:

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

pipe = pipeline("text-generation", model="alexandreteles/bonito-v1-awq")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("alexandreteles/bonito-v1-awq")
model = AutoModelForCausalLM.from_pretrained("alexandreteles/bonito-v1-awq")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use alexandreteles/bonito-v1-awq with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/alexandreteles/bonito-v1-awq

SGLang

How to use alexandreteles/bonito-v1-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 "alexandreteles/bonito-v1-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": "alexandreteles/bonito-v1-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 "alexandreteles/bonito-v1-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": "alexandreteles/bonito-v1-awq",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use alexandreteles/bonito-v1-awq with Docker Model Runner:
```
docker model run hf.co/alexandreteles/bonito-v1-awq
```

alexandreteles

nihalnayak commited on Mar 16, 2024

Commit

d0b7ae8

verified ·

1 Parent(s): 9897b41

Updated image path in README.md (#2)

Browse files

- Updated image path in README.md (e353bd10409bb538963376d0d70e8d5ad8f3fa6d)

Co-authored-by: Nihal Nayak <nihalnayak@users.noreply.huggingface.co>

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -25,7 +25,7 @@ You can find the original model at [BatsResearch/bonito-v1](https://huggingface.
 Bonito is an open-source model for conditional task generation: the task of converting unannotated text into task-specific training datasets for instruction tuning.
-![Bonito](https://raw.githubusercontent.com/BatsResearch/bonito/main/assets/workflow.jpg)
 ## Model Details

 Bonito is an open-source model for conditional task generation: the task of converting unannotated text into task-specific training datasets for instruction tuning.
+![Bonito](https://raw.githubusercontent.com/BatsResearch/bonito/main/assets/workflow.png)
 ## Model Details