Instructions to use avictus/oasst-sft-7-llama-30b-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use avictus/oasst-sft-7-llama-30b-4bit with Transformers:

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

pipe = pipeline("text-generation", model="avictus/oasst-sft-7-llama-30b-4bit")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("avictus/oasst-sft-7-llama-30b-4bit")
model = AutoModelForCausalLM.from_pretrained("avictus/oasst-sft-7-llama-30b-4bit", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use avictus/oasst-sft-7-llama-30b-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "avictus/oasst-sft-7-llama-30b-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "avictus/oasst-sft-7-llama-30b-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/avictus/oasst-sft-7-llama-30b-4bit

SGLang

How to use avictus/oasst-sft-7-llama-30b-4bit 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 "avictus/oasst-sft-7-llama-30b-4bit" \
    --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": "avictus/oasst-sft-7-llama-30b-4bit",
		"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 "avictus/oasst-sft-7-llama-30b-4bit" \
        --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": "avictus/oasst-sft-7-llama-30b-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use avictus/oasst-sft-7-llama-30b-4bit with Docker Model Runner:
```
docker model run hf.co/avictus/oasst-sft-7-llama-30b-4bit
```

Using in with oobabooga/text-generation-webui

by latent-variable - opened Apr 29, 2023

Discussion

latent-variable

Apr 29, 2023

•

edited Apr 29, 2023

I am a bit new to using Webui, but I wanted to give this model a try to see how well it does. But every time I would try to load it I would get an error. It took me a while to realize that I had to update the webui.py

I updated the following line
'''
run_cmd("python server.py --chat --model-menu") # put your flags here!
'''
with
'''
run_cmd("python server.py --chat --model oasst-sft-7-llama-30b-4bit --wbits 4 --model_type llama")
'''

If anyone is curious the model requires >18GB of VRAM

cleverest

May 15, 2023

I don't have this line in that PY file... "run_cmd("python server.py --chat --model-menu") # put your flags here!"
Ideas?

avictus

Owner May 15, 2023

I don't have this line in that PY file... "run_cmd("python server.py --chat --model-menu") # put your flags here!"
Ideas?

Are you using Windows or Linux?

cleverest

May 22, 2023

I don't have this line in that PY file... "run_cmd("python server.py --chat --model-menu") # put your flags here!"
Ideas?

Are you using Windows or Linux?

I'm using Windows 11

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