Downloads · 30 days
71
1% of all-time downloads
4bit_quant_TomGrc_FusionNet_34Bx2_MoE_v0.1_DPO
cloudyu/4bit_quant_TomGrc_FusionNet_34Bx2_MoE_v0.1_DPO
4bit_quant_TomGrc_FusionNet_34Bx2_MoE_v0.1_DPO is a text generation model from cloudyu. 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.
this is a 4 bit DPO fine-tuned MoE model for TomGrc/FusionNet34Bx2MoEv0.1
All-time downloads
12K
Public
Parameters
61.7B
35.5 GB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors35.5 GB · 100%
Parameter types
How the weights are stored.
U859.9B · 97%
Try a prompt
Model card
From the Hugging Face model README
this is a 4 bit DPO fine-tuned MoE model for TomGrc/FusionNet_34Bx2_MoE_v0.1
DPO Trainer
TRL supports the DPO Trainer for training language models from preference data, as described in the paper Direct Preference Optimization: Your Language Model is Secretly a Reward Model by Rafailov et al., 2023.
Metrics
- Task
- Text Generation
- Library
- transformers
- Type
- mixtral
- License
- apache-2.0
- Created
- Feb 3, 2024
- Updated
- Jun 27, 2024