CoolFace
Modelpublic

RichardErkhov/Vivian12300_-_full_ft_model-gguf

sourceHugging Faceupdated 1y agoView on Hugging Face
0likes458downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

fullftmodel - GGUF

  • —Model creator: https://huggingface.co/Vivian12300/
  • —Original model: https://huggingface.co/Vivian12300/fullftmodel/
NameQuant methodSize
full_ft_model.Q2_K.ggufQ2_K2.96GB
full_ft_model.IQ3_XS.ggufIQ3_XS3.28GB
full_ft_model.IQ3_S.ggufIQ3_S3.43GB
full_ft_model.Q3_K_S.ggufQ3KS3.41GB
full_ft_model.IQ3_M.ggufIQ3_M3.52GB
full_ft_model.Q3_K.ggufQ3_K3.74GB
full_ft_model.Q3_K_M.ggufQ3KM3.74GB
full_ft_model.Q3_K_L.ggufQ3KL4.03GB
full_ft_model.IQ4_XS.ggufIQ4_XS4.18GB
full_ft_model.Q4_0.ggufQ4_04.34GB
full_ft_model.IQ4_NL.ggufIQ4_NL4.38GB
full_ft_model.Q4_K_S.ggufQ4KS4.37GB
full_ft_model.Q4_K.ggufQ4_K4.58GB
full_ft_model.Q4_K_M.ggufQ4KM4.58GB
full_ft_model.Q4_1.ggufQ4_14.78GB
full_ft_model.Q5_0.ggufQ5_05.21GB
full_ft_model.Q5_K_S.ggufQ5KS5.21GB
full_ft_model.Q5_K.ggufQ5_K5.34GB
full_ft_model.Q5_K_M.ggufQ5KM5.34GB
full_ft_model.Q5_1.ggufQ5_15.65GB
full_ft_model.Q6_K.ggufQ6_K6.14GB
full_ft_model.Q8_0.ggufQ8_07.95GB

Original model description: --- libraryname: transformers license: llama3.1 basemodel: meta-llama/Llama-3.1-8B-Instruct tags:

  • —trl
  • —sft
  • —generatedfromtrainer datasets:
  • —generator model-index:
  • —name: fullftmodel results: [] ---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

fullftmodel

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the generator dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • —learning_rate: 5e-05
  • —trainbatchsize: 1
  • —evalbatchsize: 2
  • —seed: 42
  • —gradientaccumulationsteps: 16
  • —totaltrainbatch_size: 16
  • —optimizer: Use adafactor and the args are: No additional optimizer arguments
  • —lrschedulertype: linear
  • —num_epochs: 30

Training results

Framework versions

  • —Transformers 4.46.3
  • —Pytorch 2.3.1+cu121
  • —Datasets 2.20.0
  • —Tokenizers 0.20.3