Instructions to use timdettmers/guanaco-33b-merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use timdettmers/guanaco-33b-merged with Transformers:

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

pipe = pipeline("text-generation", model="timdettmers/guanaco-33b-merged")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("timdettmers/guanaco-33b-merged")
model = AutoModelForCausalLM.from_pretrained("timdettmers/guanaco-33b-merged")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use timdettmers/guanaco-33b-merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "timdettmers/guanaco-33b-merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "timdettmers/guanaco-33b-merged",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/timdettmers/guanaco-33b-merged

SGLang

How to use timdettmers/guanaco-33b-merged 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 "timdettmers/guanaco-33b-merged" \
    --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": "timdettmers/guanaco-33b-merged",
		"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 "timdettmers/guanaco-33b-merged" \
        --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": "timdettmers/guanaco-33b-merged",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use timdettmers/guanaco-33b-merged with Docker Model Runner:
```
docker model run hf.co/timdettmers/guanaco-33b-merged
```

Is it very slow , correct?

by carlosbdw - opened Jun 1, 2023

Discussion

carlosbdw

Jun 1, 2023

Hi , I run it on a A100 x4 station , and it generates very slow , no matter load_in_4bit=False or True , is it normal?

kajuberdut

Jun 2, 2023

I'm running a single 3090 and getting between 8 and 9 tokens per second. Not sure what "very slow" means but I would expect A100x4 to be at least double that... Maybe it's not using GPU with the way you have it set up. Are you using oobabooga/text-generation-webui or something else?

Chris126

Jun 11, 2023

•

edited Jun 11, 2023

same issue. Running with load_in_4bits on single 4090 and is around 2.5tps. I would have considered it is normal and not that bad for my specs. But I am curious w.r.t the comment from giblesnot. 9 tps for a 33B mode on a 3090 sounds really good.

kajuberdut

Jun 12, 2023

@Chris126
I'm currently using The Bloke's GPTQ quantization, and with the recent improvements to text-gen web ui (and all the related ecosystem) I'm now getting 15+ tokens per second even though I've set a power limit of 250 watts on my 3090. https://huggingface.co/TheBloke/guanaco-33B-GPTQ

Chris126

Jun 26, 2023

•

edited Jun 26, 2023

yeah, GPTQ is blazingly fast indeed. But I think did not mention this in your first answer and probably was the reason of the misunderstanding. Running inference directly on guanaco-33b-merged is slow (based on your hardware) But switching to GPTQ version solve the problem.

Anyway, thank you @giblesnot for the precision.

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