Downloads · 30 days
132
7% of all-time downloads
cloudyu_-_Truthful_DPO_cloudyu_Mixtral_34Bx2_MoE_60B-gguf
RichardErkhov/cloudyu_-_Truthful_DPO_cloudyu_Mixtral_34Bx2_MoE_60B-gguf
cloudyu_-_Truthful_DPO_cloudyu_Mixtral_34Bx2_MoE_60B-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
1.8K
Public
Repo size
686 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf795 GB · 100%
At a glance
- Access
- Public
- Created
- Oct 23, 2024
- Updated
- Oct 23, 2024
- SHA
- 4906cefe
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Truthful_DPO_cloudyu_Mixtral_34Bx2_MoE_60B - GGUF
- Model creator: https://huggingface.co/cloudyu/
- Original model: https://huggingface.co/cloudyu/Truthful_DPO_cloudyu_Mixtral_34Bx2_MoE_60B/
Original model description:
license: mit tags:
- moe
- DPO
- RL-TUNED
- DPO Trainer with dataset jondurbin/truthy-dpo-v0.1 to improve [cloudyu/Mixtral_34Bx2_MoE_60B]
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 NOT test!
- Created
- Oct 23, 2024
- Updated
- Oct 23, 2024