Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
vwxyzjn_-_ppo_zephyr_vllm_2e-6_kl_0.03_num_mini_batches_1-8bits – AI Model by RichardErkhov | AlphaNeural AI
You can deploy this model and start earning money today!
RichardErkhov
/
vwxyzjn_-_ppo_zephyr_vllm_2e-6_kl_0.03_num_mini_batches_1-8bits
like
0
safetensors
mistral
8-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
ppo_zephyr_vllm_2e-6_kl_0.03_num_mini_batches_1 - bnb 8bits
Model creator:
https://huggingface.co/vwxyzjn/
Original model:
https://huggingface.co/vwxyzjn/ppo_zephyr_vllm_2e-6_kl_0.03_num_mini_batches_1/
Original model description:
license: apache-2.0 base_model: alignment-handbook/zephyr-7b-sft-full tags:
generated_from_trainer model-index:
name: ppo_zephyr_vllm_2e-6_kl_0.03_num_mini_batches_1 results: []
ppo_zephyr_vllm_2e-6_kl_0.03_num_mini_batches_1
This model is a fine-tuned version of
alignment-handbook/zephyr-7b-sft-full
on an unknown 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: 2e-06
train_batch_size: 1
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 7
gradient_accumulation_steps: 64
total_train_batch_size: 448
total_eval_batch_size: 56
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3.0
Framework versions
Transformers 4.40.1
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.19.1
