Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
timlim123_-_zephyr-7b-sft-full-4bits – AI Model by RichardErkhov | AlphaNeural AI
You can deploy this model and start earning money today!
RichardErkhov
/
timlim123_-_zephyr-7b-sft-full-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
zephyr-7b-sft-full - bnb 4bits
Model creator:
https://huggingface.co/timlim123/
Original model:
https://huggingface.co/timlim123/zephyr-7b-sft-full/
Original model description:
license: apache-2.0 base_model: mistralai/Mistral-7B-v0.1 tags:
generated_from_trainer model-index:
name: zephyr-7b-sft-full results: []
zephyr-7b-sft-full
This model is a fine-tuned version of
mistralai/Mistral-7B-v0.1
on an unknown dataset. It achieves the following results on the evaluation set:
Loss: 0.9652
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: 16
eval_batch_size: 16
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 32
total_train_batch_size: 2048
total_eval_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
num_epochs: 1
Training results
Training Loss
Epoch
Step
Validation Loss
0.9644
0.67
68
0.9653
Framework versions
Transformers 4.35.0
Pytorch 2.1.0
Datasets 2.14.6
Tokenizers 0.14.1
