Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
ShenaoZhang_-_0.001_idpo_same_replacechosen_iter_1-4bits – AI Model by RichardErkhov | AlphaNeural AI
You can deploy this model and start earning money today!
RichardErkhov
/
ShenaoZhang_-_0.001_idpo_same_replacechosen_iter_1-4bits
like
0
safetensors
mistral
4-bit
bitsandbytes
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Quantization made by Richard Erkhov.
Github
Discord
Request more models
0.001_idpo_same_replacechosen_iter_1 - bnb 4bits
Model creator:
https://huggingface.co/ShenaoZhang/
Original model:
https://huggingface.co/ShenaoZhang/0.001_idpo_same_replacechosen_iter_1/
Original model description:
license: mit base_model: HuggingFaceH4/mistral-7b-sft-beta tags:
alignment-handbook
generated_from_trainer
trl
dpo
generated_from_trainer datasets:
HuggingFaceH4/ultrafeedback_binarized model-index:
name: 0.001_idpo_same_replacechosen_iter_1 results: []
0.001_idpo_same_replacechosen_iter_1
This model is a fine-tuned version of
HuggingFaceH4/mistral-7b-sft-beta
on the HuggingFaceH4/ultrafeedback_binarized dataset.
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: 2
total_train_batch_size: 128
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 4.36.2
Pytorch 2.1.2+cu121
Datasets 2.14.6
Tokenizers 0.15.2
