Instructions to use smpanaro/pythia-6.9b-AutoGPTQ-4bit-128g with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use smpanaro/pythia-6.9b-AutoGPTQ-4bit-128g with Transformers:

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

pipe = pipeline("text-generation", model="smpanaro/pythia-6.9b-AutoGPTQ-4bit-128g")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("smpanaro/pythia-6.9b-AutoGPTQ-4bit-128g")
model = AutoModelForCausalLM.from_pretrained("smpanaro/pythia-6.9b-AutoGPTQ-4bit-128g", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use smpanaro/pythia-6.9b-AutoGPTQ-4bit-128g with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "smpanaro/pythia-6.9b-AutoGPTQ-4bit-128g"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "smpanaro/pythia-6.9b-AutoGPTQ-4bit-128g",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/smpanaro/pythia-6.9b-AutoGPTQ-4bit-128g

SGLang

How to use smpanaro/pythia-6.9b-AutoGPTQ-4bit-128g 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 "smpanaro/pythia-6.9b-AutoGPTQ-4bit-128g" \
    --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": "smpanaro/pythia-6.9b-AutoGPTQ-4bit-128g",
		"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 "smpanaro/pythia-6.9b-AutoGPTQ-4bit-128g" \
        --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": "smpanaro/pythia-6.9b-AutoGPTQ-4bit-128g",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use smpanaro/pythia-6.9b-AutoGPTQ-4bit-128g with Docker Model Runner:
```
docker model run hf.co/smpanaro/pythia-6.9b-AutoGPTQ-4bit-128g
```

pythia-6.9b quantized to 4-bit using AutoGPTQ.

To use, first install AutoGPTQ:

pip install auto-gptq

Then load the model from the hub:

from transformers import AutoModelForCausalLM, AutoTokenizer
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig

model_name = "smpanaro/pythia-6.9b-AutoGPTQ-4bit-128g"
model = AutoGPTQForCausalLM.from_quantized(model_name)

Model	4-Bit Perplexity	16-Bit Perplexity	Delta
smpanaro/pythia-70m-AutoGPTQ-4bit-128g	49.125	-	-
smpanaro/pythia-160m-AutoGPTQ-4bit-128g	33.4375	23.3024	10.1351
smpanaro/pythia-410m-AutoGPTQ-4bit-128g	21.4688	13.9838	7.485
smpanaro/pythia-1b-AutoGPTQ-4bit-128g	12.0391	11.6178	0.4213
smpanaro/pythia-1.4b-AutoGPTQ-4bit-128g	10.9609	10.4391	0.5218
smpanaro/pythia-2.8b-AutoGPTQ-4bit-128g	9.8281	9.0028	0.8253
smpanaro/pythia-6.9b-AutoGPTQ-4bit-128g	8.5078	8.2257	0.2821

_{Wikitext perplexity measured as in the huggingface docs, lower is better}

Downloads last month: 16

Dataset used to train smpanaro/pythia-6.9b-AutoGPTQ-4bit-128g

Collection including smpanaro/pythia-6.9b-AutoGPTQ-4bit-128g

Pythia GPTQ

Collection

Pythia model family quantized using AutoGPTQ. • 7 items • Updated Mar 13, 2024