Instructions to use AgeOfAlgorithms/Llasa-1b-GPTQ-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AgeOfAlgorithms/Llasa-1b-GPTQ-4bit with Transformers:

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

pipe = pipeline("text-generation", model="AgeOfAlgorithms/Llasa-1b-GPTQ-4bit")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AgeOfAlgorithms/Llasa-1b-GPTQ-4bit")
model = AutoModelForCausalLM.from_pretrained("AgeOfAlgorithms/Llasa-1b-GPTQ-4bit")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AgeOfAlgorithms/Llasa-1b-GPTQ-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AgeOfAlgorithms/Llasa-1b-GPTQ-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AgeOfAlgorithms/Llasa-1b-GPTQ-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AgeOfAlgorithms/Llasa-1b-GPTQ-4bit

SGLang

How to use AgeOfAlgorithms/Llasa-1b-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 "AgeOfAlgorithms/Llasa-1b-GPTQ-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": "AgeOfAlgorithms/Llasa-1b-GPTQ-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 "AgeOfAlgorithms/Llasa-1b-GPTQ-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": "AgeOfAlgorithms/Llasa-1b-GPTQ-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AgeOfAlgorithms/Llasa-1b-GPTQ-4bit with Docker Model Runner:
```
docker model run hf.co/AgeOfAlgorithms/Llasa-1b-GPTQ-4bit
```

Configuration Parsing Warning:Config file tokenizer_config.json cannot be fetched (too big)

Model Description

This is a 4bit GPTQ quantization of Llasa-1B by the HKUSTAudio team. I tested using a script written by GitHub user nivibilla, linked below. The tests were successful, but the quality of the generated voice is often unusable. In case you don't believe me, I'll leave this model up here so you can test it yourself.

Model Sources

Repository: HKUSTAudio/Llasa-1B
Paper: LLaSA: Scaling Train-Time and Inference-Time Compute for LLaMA-based Speech Synthesis (Coming soon)
Test Script: https://github.com/slives-lab/local-llasa-tts_voice/blob/main/llasa_vllm_longtext_inference.ipynb

Downloads last month: 2

Safetensors

Model size

1B params

Tensor type

I32

F16

Model tree for AgeOfAlgorithms/Llasa-1b-GPTQ-4bit

Base model

meta-llama/Llama-3.2-1B-Instruct

Finetuned

HKUSTAudio/Llasa-1B

Quantized

(4)

this model