CoolFace
Modelpublic

RichardErkhov/Yhhhhhhhhh_-_final-DEC-deepseek-coder-1.3b-instruct-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes953downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

final-DEC-deepseek-coder-1.3b-instruct - GGUF

  • —Model creator: https://huggingface.co/Yhhhhhhhhh/
  • —Original model: https://huggingface.co/Yhhhhhhhhh/final-DEC-deepseek-coder-1.3b-instruct/
NameQuant methodSize
final-DEC-deepseek-coder-1.3b-instruct.Q2_K.ggufQ2_K0.52GB
final-DEC-deepseek-coder-1.3b-instruct.IQ3_XS.ggufIQ3_XS0.57GB
final-DEC-deepseek-coder-1.3b-instruct.IQ3_S.ggufIQ3_S0.6GB
final-DEC-deepseek-coder-1.3b-instruct.Q3_K_S.ggufQ3KS0.6GB
final-DEC-deepseek-coder-1.3b-instruct.IQ3_M.ggufIQ3_M0.63GB
final-DEC-deepseek-coder-1.3b-instruct.Q3_K.ggufQ3_K0.66GB
final-DEC-deepseek-coder-1.3b-instruct.Q3_K_M.ggufQ3KM0.66GB
final-DEC-deepseek-coder-1.3b-instruct.Q3_K_L.ggufQ3KL0.69GB
final-DEC-deepseek-coder-1.3b-instruct.IQ4_XS.ggufIQ4_XS0.7GB
final-DEC-deepseek-coder-1.3b-instruct.Q4_0.ggufQ4_00.72GB
final-DEC-deepseek-coder-1.3b-instruct.IQ4_NL.ggufIQ4_NL0.73GB
final-DEC-deepseek-coder-1.3b-instruct.Q4_K_S.ggufQ4KS0.76GB
final-DEC-deepseek-coder-1.3b-instruct.Q4_K.ggufQ4_K0.81GB
final-DEC-deepseek-coder-1.3b-instruct.Q4_K_M.ggufQ4KM0.81GB
final-DEC-deepseek-coder-1.3b-instruct.Q4_1.ggufQ4_10.8GB
final-DEC-deepseek-coder-1.3b-instruct.Q5_0.ggufQ5_00.87GB
final-DEC-deepseek-coder-1.3b-instruct.Q5_K_S.ggufQ5KS0.89GB
final-DEC-deepseek-coder-1.3b-instruct.Q5_K.ggufQ5_K0.93GB
final-DEC-deepseek-coder-1.3b-instruct.Q5_K_M.ggufQ5KM0.93GB
final-DEC-deepseek-coder-1.3b-instruct.Q5_1.ggufQ5_10.95GB
final-DEC-deepseek-coder-1.3b-instruct.Q6_K.ggufQ6_K1.09GB
final-DEC-deepseek-coder-1.3b-instruct.Q8_0.ggufQ8_01.33GB

Original model description: --- libraryname: transformers license: other basemodel: Yhhhhhhhhh/final-tc-deepseek-coder-1.3b-instruct tags:

  • —llama-factory
  • —full
  • —generatedfromtrainer model-index:
  • —name: nopyDECfinalsftdeepseek-coder-1.3b-instruct 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. -->

nopyDECfinalsftdeepseek-coder-1.3b-instruct

This model is a fine-tuned version of /content/drive/MyDrive/Effi-Code/LLaMA-Factory/saves/nopy_tc_final_sft_deepseek-coder-1.3b-instruct on the output dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.4482

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-06
  • —trainbatchsize: 8
  • —evalbatchsize: 1
  • —seed: 42
  • —gradientaccumulationsteps: 2
  • —totaltrainbatch_size: 16
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: cosine
  • —lrschedulerwarmup_ratio: 0.03
  • —num_epochs: 4.0

Training results

Framework versions

  • —Transformers 4.44.2
  • —Pytorch 2.5.0+cu121
  • —Datasets 2.21.0
  • —Tokenizers 0.19.1