Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Katayoon_-_DPO-ONLY-Zephyr-7B-3-iter-2-gguf – AI Model by RichardErkhov | AlphaNeural AI
You can deploy this model and start earning money today!
RichardErkhov
/
Katayoon_-_DPO-ONLY-Zephyr-7B-3-iter-2-gguf
like
0
conversational
endpoints_compatible
gguf
template
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Quantization made by Richard Erkhov.
Github
Discord
Request more models
DPO-ONLY-Zephyr-7B-3-iter-2 - GGUF
Model creator:
https://huggingface.co/Katayoon/
Original model:
https://huggingface.co/Katayoon/DPO-ONLY-Zephyr-7B-3-iter-2/
Name
Quant method
Size
DPO-ONLY-Zephyr-7B-3-iter-2.Q2_K.gguf
Q2_K
2.53GB
DPO-ONLY-Zephyr-7B-3-iter-2.IQ3_XS.gguf
IQ3_XS
2.81GB
DPO-ONLY-Zephyr-7B-3-iter-2.IQ3_S.gguf
IQ3_S
2.96GB
DPO-ONLY-Zephyr-7B-3-iter-2.Q3_K_S.gguf
Q3_K_S
2.95GB
DPO-ONLY-Zephyr-7B-3-iter-2.IQ3_M.gguf
IQ3_M
3.06GB
DPO-ONLY-Zephyr-7B-3-iter-2.Q3_K.gguf
Q3_K
3.28GB
DPO-ONLY-Zephyr-7B-3-iter-2.Q3_K_M.gguf
Q3_K_M
3.28GB
DPO-ONLY-Zephyr-7B-3-iter-2.Q3_K_L.gguf
Q3_K_L
3.56GB
DPO-ONLY-Zephyr-7B-3-iter-2.IQ4_XS.gguf
IQ4_XS
3.67GB
DPO-ONLY-Zephyr-7B-3-iter-2.Q4_0.gguf
Q4_0
3.83GB
DPO-ONLY-Zephyr-7B-3-iter-2.IQ4_NL.gguf
IQ4_NL
3.87GB
DPO-ONLY-Zephyr-7B-3-iter-2.Q4_K_S.gguf
Q4_K_S
3.86GB
DPO-ONLY-Zephyr-7B-3-iter-2.Q4_K.gguf
Q4_K
4.07GB
DPO-ONLY-Zephyr-7B-3-iter-2.Q4_K_M.gguf
Q4_K_M
4.07GB
DPO-ONLY-Zephyr-7B-3-iter-2.Q4_1.gguf
Q4_1
4.24GB
DPO-ONLY-Zephyr-7B-3-iter-2.Q5_0.gguf
Q5_0
4.65GB
DPO-ONLY-Zephyr-7B-3-iter-2.Q5_K_S.gguf
Q5_K_S
4.65GB
DPO-ONLY-Zephyr-7B-3-iter-2.Q5_K.gguf
Q5_K
4.78GB
DPO-ONLY-Zephyr-7B-3-iter-2.Q5_K_M.gguf
Q5_K_M
4.78GB
DPO-ONLY-Zephyr-7B-3-iter-2.Q5_1.gguf
Q5_1
5.07GB
DPO-ONLY-Zephyr-7B-3-iter-2.Q6_K.gguf
Q6_K
5.53GB
DPO-ONLY-Zephyr-7B-3-iter-2.Q8_0.gguf
Q8_0
7.17GB
Original model description:
license: mit base_model: Katayoon/DPO-ONLY-Zephyr-7B-3-iter-1 tags:
alignment-handbook
trl
dpo
generated_from_trainer
trl
dpo
generated_from_trainer datasets:
updated
original model-index:
name: DPO-ONLY-Zephyr-7B-3-iter-2 results: []
DPO-ONLY-Zephyr-7B-3-iter-2
This model is a fine-tuned version of
Katayoon/DPO-ONLY-Zephyr-7B-3-iter-1
on the updated and the original datasets.
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: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 16
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: 1
Training results
Framework versions
Transformers 4.40.2
Pytorch 2.1.2+cu121
Datasets 2.20.0
Tokenizers 0.19.1
