Llama
Collection
Meta-based models
•
1203 items
•
Updated
•
1
Merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Hermes with some Chain of Thought running though its veins.
Quant: https://huggingface.co/Triangle104/Hermes-Llama-3.2-CoT-Q4_K_M-GGUF
Merge Method
This model was merged using the SLERP merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
models:
- model: NousResearch/Hermes-3-Llama-3.2-3B
- model: prithivMLmods/Llama-Thinker-3B-Preview2
merge_method: slerp
base_model: NousResearch/Hermes-3-Llama-3.2-3B
dtype: bfloat16
parameters:
t: [0, 0.5, 0.7, 1, 0.7, 0.5, 0]
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 17.56 |
| IFEval (0-Shot) | 41.78 |
| BBH (3-Shot) | 23.80 |
| MATH Lvl 5 (4-Shot) | 9.14 |
| GPQA (0-shot) | 3.91 |
| MuSR (0-shot) | 5.09 |
| MMLU-PRO (5-shot) | 21.63 |
- Downloads last month
- 2
Model tree for Triangle104/Hermes-Llama-3.2-CoT
Merge model
this model
Collections including Triangle104/Hermes-Llama-3.2-CoT
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard41.780
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard23.800
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard9.140
- acc_norm on GPQA (0-shot)Open LLM Leaderboard3.910
- acc_norm on MuSR (0-shot)Open LLM Leaderboard5.090
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard21.630