Downloads · 30 days
51
0% of all-time downloads
yi-34b-200k-rawrr-dpo-1
adamo1139/yi-34b-200k-rawrr-dpo-1
yi-34b-200k-rawrr-dpo-1 is a text generation model from adamo1139. 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.
NEW STRONGER RAWRR FINETUNE COMING SOON!
All-time downloads
34.3K
Public
Parameters
34.4B
68.8 GB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors68.8 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- llama
- Access
- Public
- Created
- Jan 15, 2024
- Updated
- May 27, 2024
- SHA
- 6a515d0e
Try a prompt
Datasets
Model card
From the Hugging Face model README
NEW STRONGER RAWRR FINETUNE COMING SOON!
This model is Yi-34B-200K fine-tuned using DPO on rawrr_v1 dataset using QLoRA at ctx 200, lora_r 4 and lora_alpha 8. I then merged the adapter with base model. This model is akin to raw LLaMa 65B, it's not meant to follow instructions but instead should be useful as base for further fine-tuning.
Rawrr_v1 dataset made it so that this model issue less refusals, especially for benign topics, and is moreso completion focused rather than instruct focused. Base yi-34B-200k suffers from contamination on instruct and refusal datasets, i am attempting to fix that by training base models with DPO on rawrr dataset, making them more raw.
License: yi-license + non-commercial use only
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- apache-2.0
- Created
- Jan 15, 2024
- Updated
- May 27, 2024