llama3.1-cc-8B
mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated finetuned on flammenai/casual-conversation-DPO.
This is an experimental finetune that formats the conversation data sequentially with the Llama 3 template.
Method
Finetuned using an A100 on Google Colab for 3 epochs.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 20.13 |
| IFEval (0-Shot) | 50.68 |
| BBH (3-Shot) | 26.48 |
| MATH Lvl 5 (4-Shot) | 6.34 |
| GPQA (0-shot) | 4.70 |
| MuSR (0-shot) | 6.50 |
| MMLU-PRO (5-shot) | 26.08 |
- Downloads last month
- 61
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 nbeerbower/llama3.1-cc-8B
Base model
meta-llama/Meta-Llama-3.1-8B
Finetuned
meta-llama/Meta-Llama-3.1-8B-Instruct
Finetuned
this model
Dataset used to train nbeerbower/llama3.1-cc-8B
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard50.680
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard26.480
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard6.340
- acc_norm on GPQA (0-shot)Open LLM Leaderboard4.700
- acc_norm on MuSR (0-shot)Open LLM Leaderboard6.500
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard26.080