Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Dolphin-Llama-3.1-8B-orpo-v0.1-4bit-gguf – AI Model by EpistemeAI | AlphaNeural AI
You can deploy this model and start earning money today!
EpistemeAI
/
Dolphin-Llama-3.1-8B-orpo-v0.1-4bit-gguf
like
0
quantized
unsloth/Meta-Llama-3.1-8B-bnb-4bit
conversational
reciperesearch/dolphin-sft-v0.1-preference
dpo
en
endpoints_compatible
gguf
template
llama3.1
llama
us
sft
text-generation
text-generation-inference
transformers
trl
unsloth
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
gguf
:
q4_k_m
16-bit
This model is based on Meta Llama 3.1 8b, and is governed by the Llama 3.1 license.
Fine-tune using ORPO
Training Details
Training Data
dataset: reciperesearch/dolphin-sft-v0.1-preference
Training Procedure
ORPO techniques
Training Hyperparameters
Training regime:
{{ training_regime | default("[More Information Needed]", true)}}
TrainOutput(global_step=30, training_loss=4.25380277633667, metrics={'train_runtime': 679.3467, 'train_samples_per_second': 0.353, 'train_steps_per_second': 0.044, 'total_flos': 0.0, 'train_loss': 4.25380277633667, 'epoch': 0.015})
