Instructions to use glaiveai/glaive-function-calling-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use glaiveai/glaive-function-calling-v1 with Transformers:

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

pipe = pipeline("text-generation", model="glaiveai/glaive-function-calling-v1", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("glaiveai/glaive-function-calling-v1", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("glaiveai/glaive-function-calling-v1", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use glaiveai/glaive-function-calling-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/glaiveai/glaive-function-calling-v1

SGLang

How to use glaiveai/glaive-function-calling-v1 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 "glaiveai/glaive-function-calling-v1" \
    --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": "glaiveai/glaive-function-calling-v1",
		"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 "glaiveai/glaive-function-calling-v1" \
        --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": "glaiveai/glaive-function-calling-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use glaiveai/glaive-function-calling-v1 with Docker Model Runner:
```
docker model run hf.co/glaiveai/glaive-function-calling-v1
```

sahil2801 commited on Aug 8, 2023

Commit

d94dd60

1 Parent(s): 1109d93

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -0

README.md CHANGED Viewed

	@@ -70,3 +70,7 @@ The model can do multi-turn conversation in the above format.
70
71	We're working on providing an inference server which can act as a drop in replacement to the OpenAI API, you can follow [this](https://github.com/glaive-ai/function-calling-server) repo for the server.
72

 We're working on providing an inference server which can act as a drop in replacement to the OpenAI API, you can follow [this](https://github.com/glaive-ai/function-calling-server) repo for the server.
+## Known Limitations:
+- While the model does well on function calling use-cases, it doesn't always generalize very well to other chat use-cases. This is intentional as our thesis at Glaive is to provide use-case specialised model that are only used for the given task.
+- The model may sometimes hallucinate functions, v2 of the model will be aimed to fix that with a bigger dataset.