iproskurina / opt-6.7b-gptq-4bit

huggingface.co
Total runs: 90
24-hour runs: 0
7-day runs: 0
30-day runs: 0
Model's Last Updated: January 28 2024
text-generation

Introduction of opt-6.7b-gptq-4bit

Model Details of opt-6.7b-gptq-4bit

OPT-6.7B - GPTQ

The model published in this repo was quantized to 4bit using AutoGPTQ .

Quantization details

All quantization parameters were taken from GPTQ paper .

GPTQ calibration data consisted of 128 random 2048 token segments from the C4 dataset .

The grouping size used for quantization is equal to 128.

How to use this GPTQ model from Python code
Install the necessary packages
pip install accelerate==0.26.1 datasets==2.16.1 dill==0.3.7 gekko==1.0.6 multiprocess==0.70.15 peft==0.7.1 rouge==1.0.1 sentencepiece==0.1.99
git clone https://github.com/upunaprosk/AutoGPTQ
cd AutoGPTQ
pip install -v .

Recommended transformers version: 4.35.2.

You can then use the following code

from transformers import AutoTokenizer, TextGenerationPipeline,AutoModelForCausalLM
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
pretrained_model_dir = "iproskurina/opt-6.7b-gptq-4bit"
tokenizer = AutoTokenizer.from_pretrained(pretrained_model_dir, use_fast=True)
model = AutoGPTQForCausalLM.from_quantized(pretrained_model_dir, device="cuda:0", model_basename="model")
pipeline = TextGenerationPipeline(model=model, tokenizer=tokenizer)
print(pipeline("auto-gptq is")[0]["generated_text"])

LICENSE

Runs of iproskurina opt-6.7b-gptq-4bit on huggingface.co

90
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs

More Information About opt-6.7b-gptq-4bit huggingface.co Model

More opt-6.7b-gptq-4bit license Visit here:

https://choosealicense.com/licenses/other

opt-6.7b-gptq-4bit huggingface.co

opt-6.7b-gptq-4bit huggingface.co is an AI model on huggingface.co that provides opt-6.7b-gptq-4bit's model effect (), which can be used instantly with this iproskurina opt-6.7b-gptq-4bit model. huggingface.co supports a free trial of the opt-6.7b-gptq-4bit model, and also provides paid use of the opt-6.7b-gptq-4bit. Support call opt-6.7b-gptq-4bit model through api, including Node.js, Python, http.

opt-6.7b-gptq-4bit huggingface.co Url

https://huggingface.co/iproskurina/opt-6.7b-gptq-4bit

iproskurina opt-6.7b-gptq-4bit online free

opt-6.7b-gptq-4bit huggingface.co is an online trial and call api platform, which integrates opt-6.7b-gptq-4bit's modeling effects, including api services, and provides a free online trial of opt-6.7b-gptq-4bit, you can try opt-6.7b-gptq-4bit online for free by clicking the link below.

iproskurina opt-6.7b-gptq-4bit online free url in huggingface.co:

https://huggingface.co/iproskurina/opt-6.7b-gptq-4bit

opt-6.7b-gptq-4bit install

opt-6.7b-gptq-4bit is an open source model from GitHub that offers a free installation service, and any user can find opt-6.7b-gptq-4bit on GitHub to install. At the same time, huggingface.co provides the effect of opt-6.7b-gptq-4bit install, users can directly use opt-6.7b-gptq-4bit installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

opt-6.7b-gptq-4bit install url in huggingface.co:

https://huggingface.co/iproskurina/opt-6.7b-gptq-4bit

Url of opt-6.7b-gptq-4bit

opt-6.7b-gptq-4bit huggingface.co Url

Provider of opt-6.7b-gptq-4bit huggingface.co

iproskurina
ORGANIZATIONS

Other API from iproskurina

huggingface.co

Total runs: 63
Run Growth: -18
Growth Rate: -28.57%
Updated:July 23 2023