CoolFace
Modelpublic

RichardErkhov/as-cle-bert_-_tiny-fungal-llama-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes41downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

tiny-fungal-llama - GGUF

  • —Model creator: https://huggingface.co/as-cle-bert/
  • —Original model: https://huggingface.co/as-cle-bert/tiny-fungal-llama/
NameQuant methodSize
tiny-fungal-llama.Q2_K.ggufQ2_K0.4GB
tiny-fungal-llama.IQ3_XS.ggufIQ3_XS0.44GB
tiny-fungal-llama.IQ3_S.ggufIQ3_S0.47GB
tiny-fungal-llama.Q3_K_S.ggufQ3KS0.47GB
tiny-fungal-llama.IQ3_M.ggufIQ3_M0.48GB
tiny-fungal-llama.Q3_K.ggufQ3_K0.51GB
tiny-fungal-llama.Q3_K_M.ggufQ3KM0.51GB
tiny-fungal-llama.Q3_K_L.ggufQ3KL0.55GB
tiny-fungal-llama.IQ4_XS.ggufIQ4_XS0.57GB
tiny-fungal-llama.Q4_0.ggufQ4_00.59GB
tiny-fungal-llama.IQ4_NL.ggufIQ4_NL0.6GB
tiny-fungal-llama.Q4_K_S.ggufQ4KS0.6GB
tiny-fungal-llama.Q4_K.ggufQ4_K0.62GB
tiny-fungal-llama.Q4_K_M.ggufQ4KM0.62GB
tiny-fungal-llama.Q4_1.ggufQ4_10.65GB
tiny-fungal-llama.Q5_0.ggufQ5_00.71GB
tiny-fungal-llama.Q5_K_S.ggufQ5KS0.71GB
tiny-fungal-llama.Q5_K.ggufQ5_K0.73GB
tiny-fungal-llama.Q5_K_M.ggufQ5KM0.73GB
tiny-fungal-llama.Q5_1.ggufQ5_10.77GB
tiny-fungal-llama.Q6_K.ggufQ6_K0.84GB
tiny-fungal-llama.Q8_0.ggufQ8_01.09GB

Original model description: --- license: apache-2.0 base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0 tags:

  • —generatedfromtrainer model-index:
  • —name: tiny-fungal-llama 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. -->

tiny-fungal-llama

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 on the None dataset. It achieves the following results on the evaluation set:

  • —Loss: 2.0136

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: 2e-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

Training results

Training LossEpochStepValidation Loss
No log1.0271.7950
No log2.0541.8646
No log3.0812.0136

Framework versions

  • —Transformers 4.38.1
  • —Pytorch 2.1.2+cpu
  • —Datasets 2.18.0
  • —Tokenizers 0.15.2