Downloads · 30 days
48
0% of all-time downloads
sonthenguyen/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-corrupted
OpenHermes-2.5-Mistral-7B-mt-bench-DPO-corrupted is a text generation model from sonthenguyen. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Training hyperparameters LoRA: r=16 loraalpha=16 loradropout=0.05 bias="none" tasktype="CAUSALLM" targetmodules=['kproj', 'gateproj', 'vproj', 'upproj', 'qproj', 'oproj', 'downproj']
Downloads · 30 days
48
0% of all-time downloads
All-time downloads
10.9K
Public
Parameters
7.2B
14.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors14.5 GB · 100%
From the Hugging Face model README
Training hyperparameters LoRA: r=16 lora_alpha=16 lora_dropout=0.05 bias="none" task_type="CAUSAL_LM" target_modules=['k_proj', 'gate_proj', 'v_proj', 'up_proj', 'q_proj', 'o_proj', 'down_proj']
Training arguments: auto_find_batch_size=True gradient_checkpointing=True learning_rate=5e-7 lr_scheduler_type="cosine" max_steps=3922 optim="paged_adamw_32bit" warmup_steps=100
DPOTrainer: beta=0.1 max_prompt_length=1024 max_length=1536