Downloads · 30 days
6
0% of all-time downloads
Breeze-7B-Instruct-v0_1-GPTQ
MaziyarPanahi/Breeze-7B-Instruct-v0_1-GPTQ
Breeze-7B-Instruct-v0_1-GPTQ is a text generation model from MaziyarPanahi. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
MaziyarPanahi/Breeze-7B-Instruct-v01-GPTQ is a quantized (GPTQ) version of MediaTek-Research/Breeze-7B-Instruct-v01
All-time downloads
1.6K
Public
Parameters
1.4B
4.7 GB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors4.6 GB · 100%
Parameter types
How the weights are stored.
I32880M · 61%
Try a prompt
Base models
Model card
From the Hugging Face model README
Description
MaziyarPanahi/Breeze-7B-Instruct-v0_1-GPTQ is a quantized (GPTQ) version of MediaTek-Research/Breeze-7B-Instruct-v0_1
How to use
Install the necessary packages
pip install --upgrade accelerate auto-gptq transformers
Example Python code
from transformers import AutoTokenizer, pipeline
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
import torch
model_id = "MaziyarPanahi/Breeze-7B-Instruct-v0_1-GPTQ"
quantize_config = BaseQuantizeConfig(
bits=4,
group_size=128,
desc_act=False
)
model = AutoGPTQForCausalLM.from_quantized(
model_id,
use_safetensors=True,
device="cuda:0",
quantize_config=quantize_config)
tokenizer = AutoTokenizer.from_pretrained(model_id)
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
temperature=0.7,
top_p=0.95,
repetition_penalty=1.1
)
outputs = pipe("What is a large language model?")
print(outputs[0]["generated_text"])
- Task
- Text Generation
- Library
- transformers
- Type
- mistral
- License
- apache-2.0
- Created
- Jan 19, 2024
- Updated
- Jan 19, 2024