merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the Model Stock merge method using bluuwhale/L3-SthenoMaid-8B-V1 + kik41/lora-formality-informal-llama-3-8b as a base.
Models Merged
The following models were included in the merge:
- Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base + kloodia/lora-8b-medic
- mlabonne/Hermes-3-Llama-3.1-8B-lorablated + kloodia/lora-8b-physic
- Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B + kik41/lora-sarcasm-more-llama-3-8b-v2
- VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct + kloodia/lora-8b-math
- SicariusSicariiStuff/Impish_Mind_8B + kik41/lora-type-expository-llama-3-8b-v2
Configuration
The following YAML configuration was used to produce this model:
models:
- model: VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct+kloodia/lora-8b-math
- model: Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base+kloodia/lora-8b-medic
- model: mlabonne/Hermes-3-Llama-3.1-8B-lorablated+kloodia/lora-8b-physic
- model: Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B+kik41/lora-sarcasm-more-llama-3-8b-v2
- model: SicariusSicariiStuff/Impish_Mind_8B+kik41/lora-type-expository-llama-3-8b-v2
merge_method: model_stock
base_model: bluuwhale/L3-SthenoMaid-8B-V1+kik41/lora-formality-informal-llama-3-8b
normalize: false
int8_mask: true
dtype: bfloat16
Open LLM Leaderboard Evaluation Results
Detailed results can be found here! Summarized results can be found here!
| Metric | Value (%) |
|---|---|
| Average | 29.09 |
| IFEval (0-Shot) | 72.05 |
| BBH (3-Shot) | 34.28 |
| MATH Lvl 5 (4-Shot) | 17.60 |
| GPQA (0-shot) | 6.82 |
| MuSR (0-shot) | 12.32 |
| MMLU-PRO (5-shot) | 31.45 |
- Downloads last month
- 42
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for DreadPoor/Wannabe-8B-Model_Stock
Merge model
this model
Evaluation results
- averaged accuracy on IFEval (0-Shot)Open LLM Leaderboard72.050
- normalized accuracy on BBH (3-Shot)test set Open LLM Leaderboard34.280
- exact match on MATH Lvl 5 (4-Shot)test set Open LLM Leaderboard17.600
- acc_norm on GPQA (0-shot)Open LLM Leaderboard6.820
- acc_norm on MuSR (0-shot)Open LLM Leaderboard12.320
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard31.450