Instructions to use ausboss/llama-30b-supercot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ausboss/llama-30b-supercot with Transformers:

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

pipe = pipeline("text-generation", model="ausboss/llama-30b-supercot")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ausboss/llama-30b-supercot")
model = AutoModelForCausalLM.from_pretrained("ausboss/llama-30b-supercot")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ausboss/llama-30b-supercot with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ausboss/llama-30b-supercot"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ausboss/llama-30b-supercot",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ausboss/llama-30b-supercot

SGLang

How to use ausboss/llama-30b-supercot 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 "ausboss/llama-30b-supercot" \
    --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": "ausboss/llama-30b-supercot",
		"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 "ausboss/llama-30b-supercot" \
        --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": "ausboss/llama-30b-supercot",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ausboss/llama-30b-supercot with Docker Model Runner:
```
docker model run hf.co/ausboss/llama-30b-supercot
```

Trouble running on an H100 (80GB PCIe), runs out of memory when loading to cuda device

by pheuter - opened May 23, 2023

Discussion

pheuter

May 23, 2023

The runtime appears to run out of memory when executing:

model = LlamaForCausalLM.from_pretrained("ausboss/llama-30b-supercot").to("cuda")

I'm relatively new to HF and LLMs in general, am I missing something obvious in how I'm going about trying to use this model? If I have access to multiple GPUs at once, is there a way to load this model across multiple GPUs?

Any guidance appreciated!

ComputroniumDev

May 24, 2023

•

edited May 24, 2023

Memory / Disk requirements:
https://github.com/ggerganov/llama.cpp#memorydisk-requirements

Make sure you have enough Memory for 30B parameter models, it's 60 GB if the model isn't quantized. And if it is quantized you're gonna need 19.5 GB.
Keep in mind, this is the minimum memory required for 30B parameter models

pheuter

May 24, 2023

Definitely have enough memory for it, have 80GB in fact, but that still appears to not be enough for this model.

slotreck

May 25, 2023

•

edited May 25, 2023

No idea if this will be helpful in your case, but I found the other day that I would get OOM errors if I didn't have torch compiled with GPU support; once I went and re-installed torch via their instructions, those errors went away!

EDIT: Also wanted to say that in case it's truly an issue with not having enough memory, the quantization @ComputroniumDev referred to is explained here, and that also helped me quite a bit! There are some models I'm only able to load in 8 bit, and can't load without it.

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