Fine-tunes
Collection
6 items
•
Updated
•
2
Excalibur-7b-DPO
An initial foray into the world of fine-tuning. The goal of this release was to amplify the quality of the original model's responses, in particular for vision use cases*
Weighted (Importance Matrix) Quants available here
Static (Legacy) quants available here
Notes & Methodology
- Excalibur-7b fine-tuned with Direct Preference Optimization (DPO) using Intel/orca_dpo_pairs
- This is a quick experiment to determine the impact of DPO finetuning on the Excelsior-7b base model
- Ran for a little over an hour on a single A100
- Fine-tuning succeeded in making model conversational and more well-rounded
- Benchmark scores increased in the following categories versus base Excelsior-7b:
- ARC: 69.71 -> 70.9
- HellaSwag: 87.56 -> 87.93
- TruthfulQA: 67.24 -> 70.82
- Average: 73.6 -> 73.84
- Precision: bfloat16
Sample Question - Vision
*Requires additional mmproj file. You have two options for vision functionality (available inside this repo):
Select the gguf file of your choice in Koboldcpp as usual, then make sure to choose the mmproj file above in the LLaVA mmproj field of the model submenu:
Prompt Format
- For best results please use ChatML for the prompt format. Alpaca may also work.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 73.84 |
| AI2 Reasoning Challenge (25-Shot) | 70.90 |
| HellaSwag (10-Shot) | 87.93 |
| MMLU (5-Shot) | 65.46 |
| TruthfulQA (0-shot) | 70.82 |
| Winogrande (5-shot) | 82.48 |
| GSM8k (5-shot) | 65.43 |
- Downloads last month
- 103
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 InferenceIllusionist/Excalibur-7b-DPO
Base model
InferenceIllusionist/Excalibur-7bDataset used to train InferenceIllusionist/Excalibur-7b-DPO
Spaces using InferenceIllusionist/Excalibur-7b-DPO 6
Collection including InferenceIllusionist/Excalibur-7b-DPO
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard70.900
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard87.930
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard65.460
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard70.820
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard82.480
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard65.430