You can deploy this model and start earning money today!

RichardErkhov/
NicholasCorrado_-_zephyr-7b-uf-dpo-2e-gguf

Name: NicholasCorrado_-_zephyr-7b-uf-dpo-2e-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

zephyr-7b-uf-dpo-2e - GGUF

Model creator: https://huggingface.co/NicholasCorrado/
Original model: https://huggingface.co/NicholasCorrado/zephyr-7b-uf-dpo-2e/

Name	Quant method	Size
zephyr-7b-uf-dpo-2e.Q2_K.gguf	Q2_K	2.53GB
zephyr-7b-uf-dpo-2e.IQ3_XS.gguf	IQ3_XS	2.81GB
zephyr-7b-uf-dpo-2e.IQ3_S.gguf	IQ3_S	2.96GB
zephyr-7b-uf-dpo-2e.Q3_K_S.gguf	Q3_K_S	2.95GB
zephyr-7b-uf-dpo-2e.IQ3_M.gguf	IQ3_M	3.06GB
zephyr-7b-uf-dpo-2e.Q3_K.gguf	Q3_K	3.28GB
zephyr-7b-uf-dpo-2e.Q3_K_M.gguf	Q3_K_M	3.28GB
zephyr-7b-uf-dpo-2e.Q3_K_L.gguf	Q3_K_L	3.56GB
zephyr-7b-uf-dpo-2e.IQ4_XS.gguf	IQ4_XS	3.67GB
zephyr-7b-uf-dpo-2e.Q4_0.gguf	Q4_0	3.83GB
zephyr-7b-uf-dpo-2e.IQ4_NL.gguf	IQ4_NL	3.87GB
zephyr-7b-uf-dpo-2e.Q4_K_S.gguf	Q4_K_S	3.86GB
zephyr-7b-uf-dpo-2e.Q4_K.gguf	Q4_K	4.07GB
zephyr-7b-uf-dpo-2e.Q4_K_M.gguf	Q4_K_M	4.07GB
zephyr-7b-uf-dpo-2e.Q4_1.gguf	Q4_1	4.24GB
zephyr-7b-uf-dpo-2e.Q5_0.gguf	Q5_0	4.65GB
zephyr-7b-uf-dpo-2e.Q5_K_S.gguf	Q5_K_S	4.65GB
zephyr-7b-uf-dpo-2e.Q5_K.gguf	Q5_K	4.78GB
zephyr-7b-uf-dpo-2e.Q5_K_M.gguf	Q5_K_M	4.78GB
zephyr-7b-uf-dpo-2e.Q5_1.gguf	Q5_1	5.07GB
zephyr-7b-uf-dpo-2e.Q6_K.gguf	Q6_K	5.53GB
zephyr-7b-uf-dpo-2e.Q8_0.gguf	Q8_0	7.17GB

Original model description:

library_name: transformers license: apache-2.0 base_model: alignment-handbook/zephyr-7b-sft-full tags:

alignment-handbook
trl
dpo
generated_from_trainer
trl
dpo
generated_from_trainer datasets:
HuggingFaceH4/ultrafeedback_binarized model-index:
name: zephyr-7b-uf-dpo-2e results: []

zephyr-7b-uf-dpo-2e

This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set:

Loss: 0.5017
Rewards/chosen: -1.6430
Rewards/rejected: -2.9109
Rewards/accuracies: 0.7891
Rewards/margins: 1.2679
Logps/rejected: -553.7540
Logps/chosen: -426.9287
Logits/rejected: 2.3524
Logits/chosen: 1.4100

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-07
train_batch_size: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 4
total_train_batch_size: 256
total_eval_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.5424	0.5021	120	0.5378	-0.5794	-1.3437	0.7578	0.7642	-397.0288	-320.5744	-0.5261	-0.7461
0.4857	1.0042	240	0.5071	-0.9384	-1.8536	0.7695	0.9153	-448.0264	-356.4662	0.8934	0.1618
0.3605	1.5063	360	0.4996	-1.5624	-2.7607	0.7734	1.1983	-538.7272	-418.8674	2.1269	1.2559

Framework versions

Transformers 4.44.1
Pytorch 2.1.2+cu121
Datasets 2.21.0
Tokenizers 0.19.1

RichardErkhov/NicholasCorrado_-_zephyr-7b-uf-dpo-2e-gguf

Original model description:

zephyr-7b-uf-dpo-2e

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

RichardErkhov/
NicholasCorrado_-_zephyr-7b-uf-dpo-2e-gguf