mnoukhov_-_pythia410m-sft-tldr-gguf – AI Model by RichardErkhov | AlphaNeural AI

You can deploy this model and start earning money today!

RichardErkhov/
mnoukhov_-_pythia410m-sft-tldr-gguf

like

0

endpoints_compatible

Views

No views yet

Quantization made by Richard Erkhov.

Request more models

pythia410m-sft-tldr - GGUF

Model creator: https://huggingface.co/mnoukhov/
Original model: https://huggingface.co/mnoukhov/pythia410m-sft-tldr/

Name	Quant method	Size
pythia410m-sft-tldr.Q2_K.gguf	Q2_K	0.16GB
pythia410m-sft-tldr.IQ3_XS.gguf	IQ3_XS	0.18GB
pythia410m-sft-tldr.IQ3_S.gguf	IQ3_S	0.18GB
pythia410m-sft-tldr.Q3_K_S.gguf	Q3_K_S	0.18GB
pythia410m-sft-tldr.IQ3_M.gguf	IQ3_M	0.2GB
pythia410m-sft-tldr.Q3_K.gguf	Q3_K	0.21GB
pythia410m-sft-tldr.Q3_K_M.gguf	Q3_K_M	0.21GB
pythia410m-sft-tldr.Q3_K_L.gguf	Q3_K_L	0.22GB
pythia410m-sft-tldr.IQ4_XS.gguf	IQ4_XS	0.22GB
pythia410m-sft-tldr.Q4_0.gguf	Q4_0	0.23GB
pythia410m-sft-tldr.IQ4_NL.gguf	IQ4_NL	0.23GB
pythia410m-sft-tldr.Q4_K_S.gguf	Q4_K_S	0.23GB
pythia410m-sft-tldr.Q4_K.gguf	Q4_K	0.25GB
pythia410m-sft-tldr.Q4_K_M.gguf	Q4_K_M	0.25GB
pythia410m-sft-tldr.Q4_1.gguf	Q4_1	0.25GB
pythia410m-sft-tldr.Q5_0.gguf	Q5_0	0.27GB
pythia410m-sft-tldr.Q5_K_S.gguf	Q5_K_S	0.27GB
pythia410m-sft-tldr.Q5_K.gguf	Q5_K	0.28GB
pythia410m-sft-tldr.Q5_K_M.gguf	Q5_K_M	0.28GB
pythia410m-sft-tldr.Q5_1.gguf	Q5_1	0.29GB
pythia410m-sft-tldr.Q6_K.gguf	Q6_K	0.31GB
pythia410m-sft-tldr.Q8_0.gguf	Q8_0	0.4GB

Original model description:

license: apache-2.0 base_model: EleutherAI/pythia-410m-deduped tags:

generated_from_trainer model-index:
name: pythia410m-sft-tldr results: []

pythia410m-sft-tldr

This model is a fine-tuned version of EleutherAI/pythia-410m-deduped on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 2.5290

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: 1e-05
train_batch_size: 32
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
num_epochs: 1.0

Training results

Name	Quant method	Size
pythia410m-sft-tldr.Q2_K.gguf	Q2_K	0.16GB
pythia410m-sft-tldr.IQ3_XS.gguf	IQ3_XS	0.18GB
pythia410m-sft-tldr.IQ3_S.gguf	IQ3_S	0.18GB
pythia410m-sft-tldr.Q3_K_S.gguf	Q3_K_S	0.18GB
pythia410m-sft-tldr.IQ3_M.gguf	IQ3_M	0.2GB
pythia410m-sft-tldr.Q3_K.gguf	Q3_K	0.21GB
pythia410m-sft-tldr.Q3_K_M.gguf	Q3_K_M	0.21GB
pythia410m-sft-tldr.Q3_K_L.gguf	Q3_K_L	0.22GB
pythia410m-sft-tldr.IQ4_XS.gguf	IQ4_XS	0.22GB
pythia410m-sft-tldr.Q4_0.gguf	Q4_0	0.23GB
pythia410m-sft-tldr.IQ4_NL.gguf	IQ4_NL	0.23GB
pythia410m-sft-tldr.Q4_K_S.gguf	Q4_K_S	0.23GB
pythia410m-sft-tldr.Q4_K.gguf	Q4_K	0.25GB
pythia410m-sft-tldr.Q4_K_M.gguf	Q4_K_M	0.25GB
pythia410m-sft-tldr.Q4_1.gguf	Q4_1	0.25GB
pythia410m-sft-tldr.Q5_0.gguf	Q5_0	0.27GB
pythia410m-sft-tldr.Q5_K_S.gguf	Q5_K_S	0.27GB
pythia410m-sft-tldr.Q5_K.gguf	Q5_K	0.28GB
pythia410m-sft-tldr.Q5_K_M.gguf	Q5_K_M	0.28GB
pythia410m-sft-tldr.Q5_1.gguf	Q5_1	0.29GB
pythia410m-sft-tldr.Q6_K.gguf	Q6_K	0.31GB
pythia410m-sft-tldr.Q8_0.gguf	Q8_0	0.4GB

Framework versions

Transformers 4.40.2
Pytorch 2.2.1+cu121
Datasets 2.19.1
Tokenizers 0.19.1