Modelpublic

RichardErkhov/frett_-_clm-gpt2-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face

0likes57downloads

Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

clm-gpt2 - GGUF

—Model creator: https://huggingface.co/frett/
—Original model: https://huggingface.co/frett/clm-gpt2/

Name	Quant method	Size
clm-gpt2.Q2_K.gguf	Q2_K	0.08GB
clm-gpt2.IQ3_XS.gguf	IQ3_XS	0.08GB
clm-gpt2.IQ3_S.gguf	IQ3_S	0.08GB
clm-gpt2.Q3_K_S.gguf	Q3KS	0.08GB
clm-gpt2.IQ3_M.gguf	IQ3_M	0.09GB
clm-gpt2.Q3_K.gguf	Q3_K	0.09GB
clm-gpt2.Q3_K_M.gguf	Q3KM	0.09GB
clm-gpt2.Q3_K_L.gguf	Q3KL	0.1GB
clm-gpt2.IQ4_XS.gguf	IQ4_XS	0.1GB
clm-gpt2.Q4_0.gguf	Q4_0	0.1GB
clm-gpt2.IQ4_NL.gguf	IQ4_NL	0.1GB
clm-gpt2.Q4_K_S.gguf	Q4KS	0.1GB
clm-gpt2.Q4_K.gguf	Q4_K	0.11GB
clm-gpt2.Q4_K_M.gguf	Q4KM	0.11GB
clm-gpt2.Q4_1.gguf	Q4_1	0.11GB
clm-gpt2.Q5_0.gguf	Q5_0	0.11GB
clm-gpt2.Q5_K_S.gguf	Q5KS	0.11GB
clm-gpt2.Q5_K.gguf	Q5_K	0.12GB
clm-gpt2.Q5_K_M.gguf	Q5KM	0.12GB
clm-gpt2.Q5_1.gguf	Q5_1	0.12GB
clm-gpt2.Q6_K.gguf	Q6_K	0.13GB
clm-gpt2.Q8_0.gguf	Q8_0	0.17GB

Original model description: --- libraryname: transformers license: mit basemodel: openai-community/gpt2 tags:

—generatedfromtrainer metrics:
—accuracy model-index:
—name: clm-gpt2 results: [] ---

clm-gpt2

This model is a fine-tuned version of openai-community/gpt2 on an unknown dataset. It achieves the following results on the evaluation set:

—Loss: 1.5054
—Accuracy: 0.6325

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: 0.003
—trainbatchsize: 4
—evalbatchsize: 4
—seed: 42
—gradientaccumulationsteps: 4
—totaltrainbatch_size: 16
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: linear
—lrschedulerwarmup_steps: 1000
—num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.4536	0.1302	500	2.1316	0.4955
2.1054	0.2603	1000	2.0124	0.5221
1.9756	0.3905	1500	1.9025	0.5453
1.8863	0.5206	2000	1.8367	0.5601
1.8283	0.6508	2500	1.7927	0.5686
1.7893	0.7809	3000	1.7585	0.5760
1.7555	0.9111	3500	1.7328	0.5815
1.7143	1.0413	4000	1.7016	0.5882
1.6697	1.1714	4500	1.6813	0.5930
1.6584	1.3016	5000	1.6615	0.5972
1.6438	1.4317	5500	1.6422	0.6009
1.6184	1.5619	6000	1.6236	0.6049
1.6086	1.6920	6500	1.6102	0.6082
1.5882	1.8222	7000	1.5938	0.6114
1.5719	1.9524	7500	1.5786	0.6148
1.5272	2.0825	8000	1.5718	0.6175
1.4971	2.2127	8500	1.5593	0.6204
1.4893	2.3428	9000	1.5475	0.6227
1.4808	2.4730	9500	1.5382	0.6251
1.4689	2.6031	10000	1.5274	0.6275
1.4572	2.7333	10500	1.5169	0.6298
1.4488	2.8635	11000	1.5106	0.6315
1.4465	2.9936	11500	1.5054	0.6325

Framework versions

—Transformers 4.44.2
—Pytorch 2.1.0+cu121
—Datasets 2.21.0
—Tokenizers 0.19.1