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

Libraries

How to use MetaIX/GPT4-X-Alpaca-30B-4bit with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

docker model run hf.co/MetaIX/GPT4-X-Alpaca-30B-4bit

SGLang

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

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

MetaIX commited on Apr 14, 2023

Commit

dbc7df4

1 Parent(s): 09dc0f0

Update README.md

Browse files

Files changed (1) hide show

README.md +13 -1

README.md CHANGED Viewed

@@ -8,10 +8,22 @@ This was made using Chansung's GPT4-Alpaca Lora: https://huggingface.co/chansung
 <p><strong><font size="5">Benchmarks</font></strong></p>
 <strong>Wikitext2</strong>: 4.481280326843262
 <strong>Ptb-New</strong>: 8.539161682128906
 <strong>C4-New</strong>: 6.451964855194092
-<strong>Note</strong>: This version does not use <i>--groupsize 128</i>, therefore evaluations are minimally higher. However, this version allows fitting the whole model at full context using only 24GB VRAM.

 <p><strong><font size="5">Benchmarks</font></strong></p>
+<p><strong><font size="4">--true-sequential --act-order</font></strong></p>
 <strong>Wikitext2</strong>: 4.481280326843262
 <strong>Ptb-New</strong>: 8.539161682128906
 <strong>C4-New</strong>: 6.451964855194092
+<strong>Note</strong>: This version does not use <i>--groupsize 128</i>, therefore evaluations are minimally higher. However, this version allows fitting the whole model at full context using only 24GB VRAM.
+<p><strong><font size="4">--true-sequential --groupsize 128</font></strong></p>
+<strong>Wikitext2</strong>: 4.285132884979248
+<strong>Ptb-New</strong>: 8.34856128692627
+<strong>C4-New</strong>: 6.292652130126953
+<strong>Note</strong>: This version uses <i>--groupsize 128</i>, resulting in better evaluations. However, it consumes more VRAM.