yam-peleg_-_Experiment24-7B-gguf – AI Model by RichardErkhov | AlphaNeural AI

You can deploy this model and start earning money today!

RichardErkhov/
yam-peleg_-_Experiment24-7B-gguf

like

0

endpoints_compatible

Views

No views yet

Quantization made by Richard Erkhov.

Request more models

Experiment24-7B - GGUF

Model creator: https://huggingface.co/yam-peleg/
Original model: https://huggingface.co/yam-peleg/Experiment24-7B/

Name	Quant method	Size
Experiment24-7B.Q2_K.gguf	Q2_K	2.53GB
Experiment24-7B.IQ3_XS.gguf	IQ3_XS	2.81GB
Experiment24-7B.IQ3_S.gguf	IQ3_S	2.96GB
Experiment24-7B.Q3_K_S.gguf	Q3_K_S	2.95GB
Experiment24-7B.IQ3_M.gguf	IQ3_M	3.06GB
Experiment24-7B.Q3_K.gguf	Q3_K	3.28GB
Experiment24-7B.Q3_K_M.gguf	Q3_K_M	3.28GB
Experiment24-7B.Q3_K_L.gguf	Q3_K_L	3.56GB
Experiment24-7B.IQ4_XS.gguf	IQ4_XS	3.67GB
Experiment24-7B.Q4_0.gguf	Q4_0	3.83GB
Experiment24-7B.IQ4_NL.gguf	IQ4_NL	3.87GB
Experiment24-7B.Q4_K_S.gguf	Q4_K_S	3.86GB
Experiment24-7B.Q4_K.gguf	Q4_K	4.07GB
Experiment24-7B.Q4_K_M.gguf	Q4_K_M	4.07GB
Experiment24-7B.Q4_1.gguf	Q4_1	4.24GB
Experiment24-7B.Q5_0.gguf	Q5_0	4.65GB
Experiment24-7B.Q5_K_S.gguf	Q5_K_S	4.65GB
Experiment24-7B.Q5_K.gguf	Q5_K	4.78GB
Experiment24-7B.Q5_K_M.gguf	Q5_K_M	4.78GB
Experiment24-7B.Q5_1.gguf	Q5_1	5.07GB
Experiment24-7B.Q6_K.gguf	Q6_K	5.53GB
Experiment24-7B.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: apache-2.0 language:

en library_name: transformers pipeline_tag: text-generation tags:
chat

Experiment24-7B

An experiment for testing and refining a specific training and evaluation pipeline research framework.

This experiment aims to identify potential optimizations, focusing on data engineering, architecture efficiency, and evaluation performance.

The goal is to evaluate the effectiveness of a new training / evaluation pipeline for LLMs.

The experiment will explore adjustments in data preprocessing, model training algorithms, and evaluation metrics to test methods for improvement.

More details in the future experiments.

license: apache-2.0