Instructions to use MetaIX/GPT4-X-Alpasta-30b-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MetaIX/GPT4-X-Alpasta-30b-4bit with Transformers:

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

pipe = pipeline("text-generation", model="MetaIX/GPT4-X-Alpasta-30b-4bit")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MetaIX/GPT4-X-Alpasta-30b-4bit")
model = AutoModelForCausalLM.from_pretrained("MetaIX/GPT4-X-Alpasta-30b-4bit")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MetaIX/GPT4-X-Alpasta-30b-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MetaIX/GPT4-X-Alpasta-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": "MetaIX/GPT4-X-Alpasta-30b-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MetaIX/GPT4-X-Alpasta-30b-4bit

SGLang

How to use MetaIX/GPT4-X-Alpasta-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 "MetaIX/GPT4-X-Alpasta-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": "MetaIX/GPT4-X-Alpasta-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 "MetaIX/GPT4-X-Alpasta-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": "MetaIX/GPT4-X-Alpasta-30b-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MetaIX/GPT4-X-Alpasta-30b-4bit with Docker Model Runner:
```
docker model run hf.co/MetaIX/GPT4-X-Alpasta-30b-4bit
```

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

Check out the documentation for more information.

Information

GPT4-X-Alpasta-30b working with Oobabooga's Text Generation Webui and KoboldAI.

This is an attempt at improving Open Assistant's performance as an instruct while retaining its excellent prose. The merge consists of Chansung's GPT4-Alpaca Lora and Open Assistant's native fine-tune.

Update 05.27.2023

Updated the ggml quantizations to be compatible with the latest version of llamacpp (again).

What's included

GPTQ: 2 quantized versions. One quantized --true-sequential and act-order optimizations, and the other was quantized using --true-sequential --groupsize 128 optimizations.

GGML: 3 quantized versions. One quantized using q4_1, another was quantized using q5_0, and the last one was quantized using q5_1.

GPU/GPTQ Usage

To use with your GPU using GPTQ pick one of the .safetensors along with all of the .jsons and .model files.

Oobabooga: If you require further instruction, see here and here

KoboldAI: If you require further instruction, see here

CPU/GGML Usage

To use your CPU using GGML(Llamacpp) you only need the single .bin ggml file.

Oobabooga: If you require further instruction, see here

KoboldAI: If you require further instruction, see here

Benchmarks

--true-sequential --act-order

Wikitext2: 4.998758792877197

Ptb-New: 9.802155494689941

C4-New: 7.341384410858154

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.

--true-sequential --groupsize 128

Wikitext2: 4.70257568359375

Ptb-New: 9.323467254638672

C4-New: 7.041860580444336

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

Downloads last month: 226