Downloads · 30 days
12
15% of all-time downloads
raincandy-u_-_Llama-3-5B-Sheard-8bits
RichardErkhov/raincandy-u_-_Llama-3-5B-Sheard-8bits
raincandy-u_-_Llama-3-5B-Sheard-8bits is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
80
Public
Parameters
5.9B
6.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.9 GB · 100%
Parameter types
How the weights are stored.
I84.8B · 82%
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Llama-3-5B-Sheard - bnb 8bits
- Model creator: https://huggingface.co/raincandy-u/
- Original model: https://huggingface.co/raincandy-u/Llama-3-5B-Sheard/
Original model description:
language:
- en pipeline_tag: text-generation tags:
- meta
- pytorch
- llama
- llama-3 license: other license_name: llama3 license_link: LICENSE datasets:
- JeanKaddour/minipile
- raincandy-u/SlimOrca-Llama-3-Preference-DPO-Pairs
Llama-3-5B-Sheard
Pruned version of Llama-3-8b.
Tool used: PrunMe, Mergekit.
Meta Llama 3 is licensed under the Meta Llama 3 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.
Training
After sliced by mergekit, the model is continue-pretrained on minipile for 1 epoch and ~100k samples. Then we trained it using ORPO on Llama-3-70b generated DPO pairs.
Disclaimer
This model is for testing purposes only, and when the system prompt is not empty, the output may repeat and not stop!
<h1><a href="https://discord.gg/Dw8SkfBm">Join our discord</a></h1>- Type
- llama
- Created
- Feb 3, 2025
- Updated
- Feb 3, 2025