Instructions to use ToolBench/ToolLLaMA-2-7b-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ToolBench/ToolLLaMA-2-7b-v2 with Transformers:

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

pipe = pipeline("text-generation", model="ToolBench/ToolLLaMA-2-7b-v2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ToolBench/ToolLLaMA-2-7b-v2")
model = AutoModelForCausalLM.from_pretrained("ToolBench/ToolLLaMA-2-7b-v2")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ToolBench/ToolLLaMA-2-7b-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ToolBench/ToolLLaMA-2-7b-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ToolBench/ToolLLaMA-2-7b-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ToolBench/ToolLLaMA-2-7b-v2

SGLang

How to use ToolBench/ToolLLaMA-2-7b-v2 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 "ToolBench/ToolLLaMA-2-7b-v2" \
    --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": "ToolBench/ToolLLaMA-2-7b-v2",
		"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 "ToolBench/ToolLLaMA-2-7b-v2" \
        --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": "ToolBench/ToolLLaMA-2-7b-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ToolBench/ToolLLaMA-2-7b-v2 with Docker Model Runner:
```
docker model run hf.co/ToolBench/ToolLLaMA-2-7b-v2
```

model size

by HeHeYeast - opened Mar 15, 2024

Discussion

HeHeYeast

Mar 15, 2024

Why is the model this big, as it has a size of 27G, which is often appear in 13B models.

YaTharThShaRma999

Mar 17, 2024

@HeHeYeast it is stored in fp32 precision instead of fp16 precision which models are usually stored in.

fp32 precision is 2x bigger and 2x slower but you can easily convert it to fp16 precision by

model.to(dtype=torch.float16)

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment