Instructions to use TheBloke/alpaca-lora-65B-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/alpaca-lora-65B-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/alpaca-lora-65B-GPTQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/alpaca-lora-65B-GPTQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/alpaca-lora-65B-GPTQ", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheBloke/alpaca-lora-65B-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/alpaca-lora-65B-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/alpaca-lora-65B-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/alpaca-lora-65B-GPTQ

SGLang

How to use TheBloke/alpaca-lora-65B-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/alpaca-lora-65B-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/alpaca-lora-65B-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/alpaca-lora-65B-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/alpaca-lora-65B-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/alpaca-lora-65B-GPTQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/alpaca-lora-65B-GPTQ
```

Error in instructions?

by Co0ode - opened Apr 26, 2023

Discussion

Co0ode

Apr 26, 2023

I'm looking to run this using the one click installer for ooba and I noticed this in the instructions. I think the model is incorrect here? I hit a few other errors so is there any discord I could go to in order to speak to someone about this?

Also any instructions for the Occams KoboldAI which supports 4bit?

cd text-generation-webui
python server.py --model medalpaca-13B-GPTQ-4bit --wbits 4 --groupsize 128 --model_type Llama # add any other command line args you want

TheBloke

Owner Apr 26, 2023

Oh yes sorry that's wrong of course. I've edited it now to be correct.

You can find me as TheBloke#9741 on these Discords:
gpt4all: https://discord.gg/QtV7qU85
alpaca-lora: https://discord.gg/Q2fX3fzQ

But for errors it's better just to post them here. I'm going for dinner in a minute so it might be a couple of hours until I can get back to you.

I have no experience of Occams KoboldAI.

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