Instructions to use MetaIX/Alpaca-30B-Int4-128G-Safetensors with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MetaIX/Alpaca-30B-Int4-128G-Safetensors with Transformers:

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

pipe = pipeline("text-generation", model="MetaIX/Alpaca-30B-Int4-128G-Safetensors")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MetaIX/Alpaca-30B-Int4-128G-Safetensors")
model = AutoModelForCausalLM.from_pretrained("MetaIX/Alpaca-30B-Int4-128G-Safetensors")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MetaIX/Alpaca-30B-Int4-128G-Safetensors with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MetaIX/Alpaca-30B-Int4-128G-Safetensors"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MetaIX/Alpaca-30B-Int4-128G-Safetensors",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MetaIX/Alpaca-30B-Int4-128G-Safetensors

SGLang

How to use MetaIX/Alpaca-30B-Int4-128G-Safetensors 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 "MetaIX/Alpaca-30B-Int4-128G-Safetensors" \
    --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": "MetaIX/Alpaca-30B-Int4-128G-Safetensors",
		"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 "MetaIX/Alpaca-30B-Int4-128G-Safetensors" \
        --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": "MetaIX/Alpaca-30B-Int4-128G-Safetensors",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MetaIX/Alpaca-30B-Int4-128G-Safetensors with Docker Model Runner:
```
docker model run hf.co/MetaIX/Alpaca-30B-Int4-128G-Safetensors
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Information

Alpaca 30B 4-bit working with GPTQ versions used in Oobabooga's Text Generation Webui and KoboldAI.

Quantized using --true-sequential and --groupsize 128 optimizations.

This was made using Chansung's 30B Alpaca Lora: https://huggingface.co/chansung/alpaca-lora-30b

Update 04.06.2023

This is a more recent merge of Chansung's Alpaca Lora which was updated using the clean alpaca dataset as of 04/06/2023 with refined training parameters

Training Parameters

num_epochs=10
cutoff_len=512
group_by_length
lora_target_modules='[q_proj,k_proj,v_proj,o_proj]'
lora_r=16
micro_batch_size=8

Benchmarks

Wikitext2: 4.473957061767578

Ptb-New: 8.682597160339355

C4-New: 6.517213344573975

Note: This version uses --groupsize 128, resulting in better evaluations. However, it consumes more VRAM.

Downloads last month: 14