Mis mezclas [Llama 3.2 - 1B]
Collection
Mezclas de los mejores modelos Llama3.2-1B existentes hasta el momento.
•
12 items
•
Updated
ASTAROTH 3.2 1B
Detalle de la Mezcla
Agarré todas mis mezclas y la metà en una mezcla definitiva.
- Novaciano/HarmfulProject-3.2-1B
- Novaciano/UNCENSORED-Sigil-of-Satan-3.2-1B
- Novaciano/BLAST_PROCESSING-3.2-1B
Configuracion
Esta configuración YAML fue usada para producir este modelo:
merge_method: model_stock
models:
- model: Novaciano/UNCENSORED-Sigil-of-Satan-3.2-1B
parameters:
weight: 1.0
- model: Novaciano/HarmfulProject-3.2-1B
parameters:
weight: 1.0
- model: Novaciano/BLAST_PROCESSING-3.2-1B
parameters:
weight: 1.0
base_model: Novaciano/La_Mejor_Mezcla-3.2-1B
dtype: bfloat16
out_dtype: bfloat16
parameters:
int8_mask: true
normalize: true
rescale: false
chat_template: auto
tokenizer:
source: union
Open LLM Leaderboard Evaluation Results
Detailed results can be found here! Summarized results can be found here!
| Metric | Value (%) |
|---|---|
| Average | 14.17 |
| IFEval (0-Shot) | 56.13 |
| BBH (3-Shot) | 9.49 |
| MATH Lvl 5 (4-Shot) | 7.33 |
| GPQA (0-shot) | 0.78 |
| MuSR (0-shot) | 1.21 |
| MMLU-PRO (5-shot) | 10.10 |
- Downloads last month
- 18
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for Novaciano/ASTAROTH-3.2-1B
Merge model
this model
Collection including Novaciano/ASTAROTH-3.2-1B
Evaluation results
- averaged accuracy on IFEval (0-Shot)Open LLM Leaderboard56.130
- normalized accuracy on BBH (3-Shot)test set Open LLM Leaderboard9.490
- exact match on MATH Lvl 5 (4-Shot)test set Open LLM Leaderboard7.330
- acc_norm on GPQA (0-shot)Open LLM Leaderboard0.780
- acc_norm on MuSR (0-shot)Open LLM Leaderboard1.210
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard10.100