Instructions to use MetaIX/Alpaca-30B-Int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MetaIX/Alpaca-30B-Int4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MetaIX/Alpaca-30B-Int4")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("MetaIX/Alpaca-30B-Int4") model = AutoModelForCausalLM.from_pretrained("MetaIX/Alpaca-30B-Int4") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use MetaIX/Alpaca-30B-Int4 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" # 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", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/MetaIX/Alpaca-30B-Int4
- SGLang
How to use MetaIX/Alpaca-30B-Int4 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" \ --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", "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" \ --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", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use MetaIX/Alpaca-30B-Int4 with Docker Model Runner:
docker model run hf.co/MetaIX/Alpaca-30B-Int4
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 --act-order optimizations.
This was made using Chansung's 30B Alpaca Lora: https://huggingface.co/chansung/alpaca-lora-30bUpdate 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: 4.608365058898926
Ptb-New: 8.69663143157959
C4-New: 6.624773979187012
Note: This version does not use --groupsize 128, therefore evaluations are minimally higher. However, this version allows fitting the whole model at full context using only 24GB VRAM.
- Downloads last month
- 72
docker model run hf.co/MetaIX/Alpaca-30B-Int4