RichardErkhov/soikit_-_class_stand_model-exl2

Quantization made by Richard Erkhov.

Github

Discord

Request more models

class_stand_model - EXL2

• Model creator: https://huggingface.co/soikit/
• Original model: https://huggingface.co/soikit/class_stand_model/

Available sizes

| Branch | Bits | Description | | ----- | ---- | ------- | ------ | ------ | ------ | ------ | ------------ | | 8_0 | 8.0 | Maximum quality that ExLlamaV2 can produce, near unquantized performance. | | 6_5 | 6.5 | Very similar to 8.0, good tradeoff of size vs performance, recommended. | | 5_0 | 5.0 | Slightly lower quality vs 6.5, but usable on 8GB cards. | | 4_25 | 4.25 | GPTQ equivalent bits per weight, slightly higher quality. | | 3_5 | 3.5 | Lower quality, only use if you have to. |

Download instructions

With git:

git clone --single-branch --branch 6_5 https://huggingface.co/soikit_-_class_stand_model-exl2 class_stand_model-6_5

With huggingface hub:

pip3 install huggingface-hub

To download a specific branch, use the --revision parameter. For example, to download the 6.5 bpw branch: Linux:

huggingface-cli download soikit_-_class_stand_model-exl2 --revision 6_5 --local-dir class_stand_model-6_5 --local-dir-use-symlinks False

Windows (which apparently doesn't like _ in folders sometimes?):

huggingface-cli download soikit_-_class_stand_model-exl2 --revision 6_5 --local-dir class_stand_model-6.5 --local-dir-use-symlinks False

Original model description:

library_name: transformers tags: - generated_from_trainer model-index: - name: class_stand_model results: []

class_stand_model

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.6650

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
• train_batch_size: 2
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_HF with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 100
• num_epochs: 50
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.9748	29	2.5157
2.5054	1.9916	59	2.4631
2.5054	2.9748	88	2.4333
2.2607	3.9916	118	2.4291
2.2607	4.9748	147	2.4790
1.8979	5.9916	177	2.5425
1.5637	6.9748	206	2.6650

Framework versions

• Transformers 4.46.1
• Pytorch 2.3.0+cu121
• Datasets 3.1.0
• Tokenizers 0.20.1