Downloads · 30 days
0
RedPajama-INCITE-Chat-3B-v1-RL-LoRA-8bit-test1
DanielSc4/RedPajama-INCITE-Chat-3B-v1-RL-LoRA-8bit-test1
RedPajama-INCITE-Chat-3B-v1-RL-LoRA-8bit-test1 is a text generation model from DanielSc4. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
Pre-trained model fine-tuned using Reinforcement Learning on DIALOCONAN dataset using facebook/roberta-hate-speech-dynabench-r4-target as reward model.
Access
Public
Updated Aug 10, 2023
Repo size
42 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin42 MB · 100%
At a glance
- Task
- Text Generation
- License
- apache-2.0
- Access
- Public
- Created
- Jun 29, 2023
- Updated
- Aug 10, 2023
- SHA
- a2ee88a9
Try a prompt
Model card
From the Hugging Face model README
Pre-trained model fine-tuned using Reinforcement Learning on DIALOCONAN dataset using facebook/roberta-hate-speech-dynabench-r4-target as reward model.
Toxicity results on allenai/real-toxicity-prompts dataset using custom prompts (see 🥞RewardLM for details).
| Toxicity Level | RedPajama-INCITE-Chat-3B |
|---|---|
| Pre-Trained | 0.217 |
| Fine-Tuned | 0.129 |
| RL (this) | 0.160 |
- Task
- Text Generation
- License
- apache-2.0
- Languages
- en
- Created
- Jun 29, 2023
- Updated
- Aug 10, 2023