Instructions to use substratusai/weaviate-gorilla-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use substratusai/weaviate-gorilla-v3 with Transformers:

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

pipe = pipeline("text-generation", model="substratusai/weaviate-gorilla-v3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("substratusai/weaviate-gorilla-v3")
model = AutoModelForCausalLM.from_pretrained("substratusai/weaviate-gorilla-v3")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use substratusai/weaviate-gorilla-v3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "substratusai/weaviate-gorilla-v3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "substratusai/weaviate-gorilla-v3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/substratusai/weaviate-gorilla-v3

SGLang

How to use substratusai/weaviate-gorilla-v3 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 "substratusai/weaviate-gorilla-v3" \
    --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": "substratusai/weaviate-gorilla-v3",
		"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 "substratusai/weaviate-gorilla-v3" \
        --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": "substratusai/weaviate-gorilla-v3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use substratusai/weaviate-gorilla-v3 with Docker Model Runner:
```
docker model run hf.co/substratusai/weaviate-gorilla-v3
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Prompt

{input}
{output}

Example: of entry used for finetuning

Your task is to write an API request for a new schema given the API reference and an example.    The user command is:    "Get me the details of 2 music tracks that are similar to the given vector."    Here is the API reference for a query that will help with this command and an example of how to use it:    {Get {JeopardyQuestion (limit: 2,nearVector: {vector: [-0.0125526935, -0.021168863, -0.01076519, ...]}}}}}    Could you please formulate this query for the following schema?    {"class": "Track","description": "A music track.","properties": [{"name": "trackId","dataType": ["uuid"],"description": "A unique identifier for each track.","moduleConfig": {"text2vec-transformers": {"skip": true,"vectorizeClassName": false,"vectorizePropertyName": false}}{"name": "title","dataType": ["text"],"description": "The title of the track.","moduleConfig": {"text2vec-transformers": {"skip": false,"vectorizeClassName": false,"vectorizePropertyName": false}}{"name": "duration","dataType": ["int"],"description": "The duration of the track in seconds.","moduleConfig": {"text2vec-transformers": {"skip": true,"vectorizeClassName": false,"vectorizePropertyName": false}}{"name": "artist","dataType": ["Artist"],"description": "The artist of the track.","moduleConfig": {"text2vec-transformers": {"skip": true,"vectorizeClassName": false,"vectorizePropertyName": false}}{"name": "album","dataType": ["Album"],"description": "The album of the track.","moduleConfig": {"text2vec-transformers": {"skip": true,"vectorizeClassName": false,"vectorizePropertyName": false}}}}    VERY IMPORTANT! Please only output the GraphQL for the query and nothing else!    
{  Get {    Track (      limit: 2,      nearVector: {        vector: [-0.0125526935, -0.021168863, -0.01076519, ...]      }    ) {      trackId      title      duration      artist {        artistId        name      }      album {        albumId        title      }    }  }}

Downloads last month: 11