Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Tiny-lama-1.3B-chat-ppo – AI Model by sehyun66 | AlphaNeural AI
You can deploy this model and start earning money today!
sehyun66
/
Tiny-lama-1.3B-chat-ppo
like
0
transformers
pytorch
safetensors
humman feedback
HH-RLHF
PPO
lama-1.3B
question-answering
en
HuggingFaceH4/ultrafeedback_binarized
apache-2.0
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
RLHF with ppo_Trainer and Lora
image/png
image/png
Hyperparameter
#ppo learning_rate=5e-6, batch_size=32, mini_batch_size=1, horizon=10000, cliprange =0.2, cliprange_value=0.2, lam=0.95, target_kl=2, use_score_scaling = True, log_with='wandb'
#lora r=16, lora_alpha=32, lora_dropout=0.05, bias="none", task_type="CAUSAL_LM",
