Llama
Collection
Meta-based models
•
1203 items
•
Updated
•
1
Merge
This is a merge of pre-trained language models created using mergekit.
Merge Method
This model was merged using the Passthrough merge method using nbeerbower/llama3.1-cc-8B + mpasila/Llama-3.1-Literotica-LoRA-8B as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
base_model: nbeerbower/llama3.1-cc-8B+mpasila/Llama-3.1-Literotica-LoRA-8B
dtype: bfloat16
merge_method: passthrough
models:
- model: nbeerbower/llama3.1-cc-8B+mpasila/Llama-3.1-Literotica-LoRA-8B
tokenizer_source: unsloth/Meta-Llama-3.1-8B
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 12.72 |
| IFEval (0-Shot) | 29.93 |
| BBH (3-Shot) | 13.87 |
| MATH Lvl 5 (4-Shot) | 0.30 |
| GPQA (0-shot) | 3.69 |
| MuSR (0-shot) | 6.24 |
| MMLU-PRO (5-shot) | 22.27 |
- Downloads last month
- 1
Model tree for Triangle104/Llama3.1-cc-Lit-8b
Merge model
this model
Collections including Triangle104/Llama3.1-cc-Lit-8b
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard29.930
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard13.870
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard0.300
- acc_norm on GPQA (0-shot)Open LLM Leaderboard3.690
- acc_norm on MuSR (0-shot)Open LLM Leaderboard6.240
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard22.270