Instructions to use kevinbazira/aya-expanse-32b-gptq-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kevinbazira/aya-expanse-32b-gptq-4bit with Transformers:

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

pipe = pipeline("text-generation", model="kevinbazira/aya-expanse-32b-gptq-4bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kevinbazira/aya-expanse-32b-gptq-4bit")
model = AutoModelForCausalLM.from_pretrained("kevinbazira/aya-expanse-32b-gptq-4bit", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kevinbazira/aya-expanse-32b-gptq-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kevinbazira/aya-expanse-32b-gptq-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kevinbazira/aya-expanse-32b-gptq-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kevinbazira/aya-expanse-32b-gptq-4bit

SGLang

How to use kevinbazira/aya-expanse-32b-gptq-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 "kevinbazira/aya-expanse-32b-gptq-4bit" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kevinbazira/aya-expanse-32b-gptq-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "kevinbazira/aya-expanse-32b-gptq-4bit" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kevinbazira/aya-expanse-32b-gptq-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kevinbazira/aya-expanse-32b-gptq-4bit with Docker Model Runner:
```
docker model run hf.co/kevinbazira/aya-expanse-32b-gptq-4bit
```

aya-expanse-32b-gptq-4bit

This repository contains a quantized version of the CohereForAI/aya-expanse-32b model using the GPTQ method in 4-bit precision.

Model Summary

Quantized Model: kevinbazira/aya-expanse-32b-gptq-4bit
Quantization Method: GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
Dataset: c4
Precision: 4-bit
Original Model: CohereForAI/aya-expanse-32b

How to Use the Quantized Model

1. Install the necessary packages

Before using the quantized model, please ensure your environment has:

AutoGPTQ

2. Run inference

Load and use the quantized model as shown below in Python:

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Set up device
device = torch.device('cuda:1') # Remember to use the correct device here

# Load model and tokenizer
model_name = "kevinbazira/aya-expanse-32b-gptq-4bit"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name, 
    device_map={"": device.index}
)

# Prepare input
# https://huggingface.co/docs/transformers/en/pad_truncation
input_text = "Add your prompt here."
inputs = tokenizer(input_text, return_tensors="pt", truncation=True, padding="max_length", max_length=64)
inputs = {key: value.to(device) for key, value in inputs.items()}

# Perform text generation 
# https://huggingface.co/docs/transformers/en/main_classes/text_generation
outputs = model.generate(
    **inputs,
    num_return_sequences=1,
    min_new_tokens=64,
    max_new_tokens=64,
    do_sample=False,
    use_cache=True,
    num_beams=1
)

# Decode and print the output
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

More Information

Original Model: For details about the original model's architecture, training dataset, and performance, please visit the CohereForAI aya-expanse-32b model card.
Support or inquiries: If you run into any issues or have questions about the quantized model, feel free to reach me via email: contact@kevinbazira.com. I'll be happy to help!

Downloads last month: 30

Safetensors

Model size

32B params

Tensor type

I32

F16

Model tree for kevinbazira/aya-expanse-32b-gptq-4bit

Base model

CohereLabs/aya-expanse-32b

Quantized

(19)

this model

Paper for kevinbazira/aya-expanse-32b-gptq-4bit

GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Paper • 2210.17323 • Published Oct 31, 2022 • 12