CoolFace
Modelpublic

RichardErkhov/argsearch_-_llama-7b-sft-float32-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes270downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama-7b-sft-float32 - GGUF

  • —Model creator: https://huggingface.co/argsearch/
  • —Original model: https://huggingface.co/argsearch/llama-7b-sft-float32/
NameQuant methodSize
llama-7b-sft-float32.Q2_K.ggufQ2_K2.36GB
llama-7b-sft-float32.IQ3_XS.ggufIQ3_XS2.6GB
llama-7b-sft-float32.IQ3_S.ggufIQ3_S2.75GB
llama-7b-sft-float32.Q3_K_S.ggufQ3KS2.75GB
llama-7b-sft-float32.IQ3_M.ggufIQ3_M2.9GB
llama-7b-sft-float32.Q3_K.ggufQ3_K3.07GB
llama-7b-sft-float32.Q3_K_M.ggufQ3KM3.07GB
llama-7b-sft-float32.Q3_K_L.ggufQ3KL3.35GB
llama-7b-sft-float32.IQ4_XS.ggufIQ4_XS3.4GB
llama-7b-sft-float32.Q4_0.ggufQ4_03.56GB
llama-7b-sft-float32.IQ4_NL.ggufIQ4_NL3.58GB
llama-7b-sft-float32.Q4_K_S.ggufQ4KS3.59GB
llama-7b-sft-float32.Q4_K.ggufQ4_K3.8GB
llama-7b-sft-float32.Q4_K_M.ggufQ4KM3.8GB
llama-7b-sft-float32.Q4_1.ggufQ4_13.95GB
llama-7b-sft-float32.Q5_0.ggufQ5_04.33GB
llama-7b-sft-float32.Q5_K_S.ggufQ5KS4.33GB
llama-7b-sft-float32.Q5_K.ggufQ5_K4.45GB
llama-7b-sft-float32.Q5_K_M.ggufQ5KM4.45GB
llama-7b-sft-float32.Q5_1.ggufQ5_14.72GB
llama-7b-sft-float32.Q6_K.ggufQ6_K5.15GB
llama-7b-sft-float32.Q8_0.ggufQ8_06.67GB

Original model description: --- tags:

  • —generatedfromtrainer model-index:
  • —name: tmp_trainer 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. -->

tmp_trainer

This model was trained from scratch on an unknown 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: 8
  • —evalbatchsize: 8
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 3.0

Framework versions

  • —Transformers 4.35.2
  • —Pytorch 2.1.1+cu121
  • —Datasets 2.15.0
  • —Tokenizers 0.15.0