Instructions to use TheBloke/gorilla-7B-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/gorilla-7B-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/gorilla-7B-GPTQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/gorilla-7B-GPTQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/gorilla-7B-GPTQ", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheBloke/gorilla-7B-GPTQ with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/TheBloke/gorilla-7B-GPTQ

SGLang

How to use TheBloke/gorilla-7B-GPTQ 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 "TheBloke/gorilla-7B-GPTQ" \
    --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": "TheBloke/gorilla-7B-GPTQ",
		"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 "TheBloke/gorilla-7B-GPTQ" \
        --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": "TheBloke/gorilla-7B-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/gorilla-7B-GPTQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/gorilla-7B-GPTQ
```

TheBloke commited on May 28, 2023

Commit

5d07dd1

1 Parent(s): f2bf68a

Update README.md

Browse files

Files changed (1) hide show

README.md +11 -0

README.md CHANGED Viewed

@@ -23,12 +23,23 @@ This repo contains a quantised 4-bit GPTQ model for [Gorilla 7B](https://hugging
 It is the result of quantising to 4bit using [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa).
 ## Other repositories available
 * [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/gorilla-7B-GPTQ)
 * [4-bit, 5-bit, and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/gorilla-7B-GGML)
 * [Merged, unquantised fp16 model in HF format](https://huggingface.co/TheBloke/gorilla-7B-fp16)
 ## How to easily download and use this model in text-generation-webui
 Open the text-generation-webui UI as normal.

 It is the result of quantising to 4bit using [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa).
+**NOTE**: This is not a regular LLM. It is designed to allow LLMs to use tools by invoking APIs.
+"Gorilla enables LLMs to use tools by invoking APIs. Given a natural language query, Gorilla can write a semantically- and syntactically- correct API to invoke. With Gorilla, we are the first to demonstrate how to use LLMs to invoke 1,600+ (and growing) API calls accurately while reducing hallucination. "
 ## Other repositories available
 * [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/gorilla-7B-GPTQ)
 * [4-bit, 5-bit, and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/gorilla-7B-GGML)
 * [Merged, unquantised fp16 model in HF format](https://huggingface.co/TheBloke/gorilla-7B-fp16)
+## Prompt template
+```
+###USER: find me an API to generate cute cat images
+###ASSISTANT:
+```
 ## How to easily download and use this model in text-generation-webui
 Open the text-generation-webui UI as normal.