RichardErkhov/abemorcal_-_ft_clm_eli5-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

ft_clm_eli5 - GGUF

• Model creator: https://huggingface.co/abemorcal/
• Original model: https://huggingface.co/abemorcal/ft_clm_eli5/

Name	Quant method	Size
ft_clm_eli5.Q2_K.gguf	Q2_K	0.06GB
ft_clm_eli5.IQ3_XS.gguf	IQ3_XS	0.07GB
ft_clm_eli5.IQ3_S.gguf	IQ3_S	0.07GB
ft_clm_eli5.Q3_K_S.gguf	Q3_K_S	0.07GB
ft_clm_eli5.IQ3_M.gguf	IQ3_M	0.07GB
ft_clm_eli5.Q3_K.gguf	Q3_K	0.07GB
ft_clm_eli5.Q3_K_M.gguf	Q3_K_M	0.07GB
ft_clm_eli5.Q3_K_L.gguf	Q3_K_L	0.07GB
ft_clm_eli5.IQ4_XS.gguf	IQ4_XS	0.07GB
ft_clm_eli5.Q4_0.gguf	Q4_0	0.08GB
ft_clm_eli5.IQ4_NL.gguf	IQ4_NL	0.08GB
ft_clm_eli5.Q4_K_S.gguf	Q4_K_S	0.08GB
ft_clm_eli5.Q4_K.gguf	Q4_K	0.08GB
ft_clm_eli5.Q4_K_M.gguf	Q4_K_M	0.08GB
ft_clm_eli5.Q4_1.gguf	Q4_1	0.08GB
ft_clm_eli5.Q5_0.gguf	Q5_0	0.09GB
ft_clm_eli5.Q5_K_S.gguf	Q5_K_S	0.09GB
ft_clm_eli5.Q5_K.gguf	Q5_K	0.09GB
ft_clm_eli5.Q5_K_M.gguf	Q5_K_M	0.09GB
ft_clm_eli5.Q5_1.gguf	Q5_1	0.09GB
ft_clm_eli5.Q6_K.gguf	Q6_K	0.1GB
ft_clm_eli5.Q8_0.gguf	Q8_0	0.12GB

Original model description:

library_name: transformers license: apache-2.0 base_model: distilbert/distilgpt2 tags: - generated_from_trainer datasets: - eli5_category model-index: - name: ft_clm_eli5 results: []

ft_clm_eli5

This model is a fine-tuned version of distilbert/distilgpt2 on the eli5_category dataset. It achieves the following results on the evaluation set:

• Loss: 3.8191

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
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
3.9502	1.0	1296	3.8309
3.8582	2.0	2592	3.8198
3.8206	3.0	3888	3.8191

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0