Instructions to use sambanovasystems/LLaMA-30b-toolbench with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sambanovasystems/LLaMA-30b-toolbench with Transformers:

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

pipe = pipeline("text-generation", model="sambanovasystems/LLaMA-30b-toolbench")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sambanovasystems/LLaMA-30b-toolbench")
model = AutoModelForCausalLM.from_pretrained("sambanovasystems/LLaMA-30b-toolbench")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use sambanovasystems/LLaMA-30b-toolbench with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sambanovasystems/LLaMA-30b-toolbench"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sambanovasystems/LLaMA-30b-toolbench",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/sambanovasystems/LLaMA-30b-toolbench

SGLang

How to use sambanovasystems/LLaMA-30b-toolbench 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 "sambanovasystems/LLaMA-30b-toolbench" \
    --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": "sambanovasystems/LLaMA-30b-toolbench",
		"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 "sambanovasystems/LLaMA-30b-toolbench" \
        --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": "sambanovasystems/LLaMA-30b-toolbench",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use sambanovasystems/LLaMA-30b-toolbench with Docker Model Runner:
```
docker model run hf.co/sambanovasystems/LLaMA-30b-toolbench
```

hongfenglu commited on Jun 16, 2023

Commit

9a18e1d

1 Parent(s): a584136

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -29,7 +29,7 @@ LLaMA-30B-toolbench is a 30 billion parameter model used for api based action ge
 ### Basic Information
 <!-- Provide the basic links for the model. -->
-- **Paper**: [Link]
 - **Github**: [link](https://github.com/sambanova/toolbench)
@@ -88,7 +88,7 @@ I have the following set of API:\n\n# To set the location for hotel search, give
 <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-The training data is curated for the 8 tasks in ToolBench. See Appendix A of the [paper](dummy link) for task details and Appendix C.1 for the training data curation details. In total, there are 9704 training samples, organized in all-shot format as described in Appendix C.2. Here is the [download link](https://drive.google.com/file/d/1lUatLGnSVhfy1uVIPEQ7qCoLtnCIXi2O/view?usp=sharing) to the training data.
 ### Training Procedure

 ### Basic Information
 <!-- Provide the basic links for the model. -->
+- **Paper**: [Link](https://arxiv.org/abs/2305.16504)
 - **Github**: [link](https://github.com/sambanova/toolbench)
 <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+The training data is curated for the 8 tasks in ToolBench. See Appendix A of the [paper](https://arxiv.org/abs/2305.16504) for task details and Appendix C.1 for the training data curation details. In total, there are 9704 training samples, organized in all-shot format as described in Appendix C.2. Here is the [download link](https://drive.google.com/file/d/1lUatLGnSVhfy1uVIPEQ7qCoLtnCIXi2O/view?usp=sharing) to the training data.
 ### Training Procedure