My Collection
Collection
16 items
•
Updated
Model Card for habib-DPO
This model is derivative version of Kunoichi-DPO-v2-7B on internal datasets.
Model Description
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by: Habibullah Akbar
- Funded by [optional]: Creasoft ID
- Shared by [optional]: Habibullah Akbar
- Model type: Auto-regressive
- Language(s) (NLP): Mostly English
- License: Apache-2.0
- Finetuned from model [optional]: Kunoichi-DPO-v2-7B
Evaluation
- Downloads last month
- 13
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for ChavyvAkvar/habib-DPO
Base model
SanjiWatsuki/Kunoichi-DPO-v2-7BCollection including ChavyvAkvar/habib-DPO
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard68.690
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard86.710
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard64.250
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard65.200
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard79.480
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard66.110