Instructions to use deepgrove/Bonsai with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use deepgrove/Bonsai with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="deepgrove/Bonsai", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("deepgrove/Bonsai", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("deepgrove/Bonsai", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use deepgrove/Bonsai with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "deepgrove/Bonsai" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "deepgrove/Bonsai", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/deepgrove/Bonsai
- SGLang
How to use deepgrove/Bonsai 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 "deepgrove/Bonsai" \ --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": "deepgrove/Bonsai", "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 "deepgrove/Bonsai" \ --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": "deepgrove/Bonsai", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use deepgrove/Bonsai with Docker Model Runner:
docker model run hf.co/deepgrove/Bonsai
Fix model path in the transformers example code (#1)
Browse files- Fix model path in the transformers example code (d9fa61dd6411ef9e8c55d2bb929a5db441fd3f97)
Co-authored-by: Pierre-Hugues Husson <phh@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -32,8 +32,8 @@ Bonsai can be easily used through the Huggingface Transformers library. However,
|
|
| 32 |
```{python}
|
| 33 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 34 |
|
| 35 |
-
tokenizer = AutoTokenizer.from_pretrained("
|
| 36 |
-
model = AutoModelForCausalLM.from_pretrained("
|
| 37 |
text = "What is the capital of France?"
|
| 38 |
inputs = tokenizer(text, return_tensors="pt")
|
| 39 |
outputs = model.generate(**inputs, max_length=100)
|
|
|
|
| 32 |
```{python}
|
| 33 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 34 |
|
| 35 |
+
tokenizer = AutoTokenizer.from_pretrained("deepgrove/Bonsai", trust_remote_code=True)
|
| 36 |
+
model = AutoModelForCausalLM.from_pretrained("deepgrove/Bonsai", trust_remote_code=True)
|
| 37 |
text = "What is the capital of France?"
|
| 38 |
inputs = tokenizer(text, return_tensors="pt")
|
| 39 |
outputs = model.generate(**inputs, max_length=100)
|