Instructions to use TheBloke/orca_mini_13B-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/orca_mini_13B-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/orca_mini_13B-GPTQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/orca_mini_13B-GPTQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/orca_mini_13B-GPTQ")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheBloke/orca_mini_13B-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/orca_mini_13B-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/orca_mini_13B-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/orca_mini_13B-GPTQ

SGLang

How to use TheBloke/orca_mini_13B-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/orca_mini_13B-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/orca_mini_13B-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/orca_mini_13B-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/orca_mini_13B-GPTQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/orca_mini_13B-GPTQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/orca_mini_13B-GPTQ
```

g_idx tensors?

by mgleize - opened Jul 1, 2023

Discussion

mgleize

Jul 1, 2023

•

edited Jul 1, 2023

Hi,

I noticed this model doesn't have ".g_idx" tensors, which apparently my inference code is looking for (latest source version of HF's text-generation-inference). Some of your other models do have them (like stable-vicuna-13B-GPTQ). I understand this possibly has something to do with GPTQ-for-LLaMa. Could anyone explain what these do at a high level? Is there a way to bypass this with my code or are these vital?

AutoGPTQ is unfortunately not the option I'd like to retain atm (I'm forced to disable Triton due to hardware bugs and it's very slow).

Btw thank you (TheBloke) for all your work getting these quantized models out so fast, truly a boon :).

TheBloke

Owner Jul 1, 2023

•

edited Jul 1, 2023

Yeah, somehow Text Generation Interface managed to merge a version of GPTQ-for-LLaMa that doesn't support the vast majority of models currently on HF.

I specifically use an older version of GPTQ-for-LLaMa to make my quants because it guaranteed compatibility with the widest range of libraries and UIs - AutoGPTQ, text-generation-webui, KobaldAI, ExLlama. This meant using an older version of the GPTQ format, but all the clients before TGI could support both the older format and the newer format. I did experiment with making GPTQ using the newer format, but then I would get complaints from certain users because their UI couldn't load it.

Now TGI has implemented a version of GPTQ-for-LLaMa that can only load the new format. They could have integrated AutoGPTQ which would have automatically supported all formats. Or they could have implemented the same compatibility code as other clients have. But they did neither.

I will re-evaluate this soon and see what I can do but I can't make any promises.

mgleize

Jul 1, 2023

Very clear, thank you!

MrAiran

Jul 31, 2023

do you know which version they update GPTQ for llama? I need to use TGI to make simultaneous requests via api

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