|
--- |
|
base_model: |
|
- TheHierophant/Underground-Cognitive-V0.3-test |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
|
|
--- |
|
# merge |
|
|
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). |
|
|
|
## Merge Details |
|
### Merge Method |
|
|
|
This model was merged using the passthrough merge method. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [TheHierophant/Underground-Cognitive-V0.3-test](https://huggingface.co/TheHierophant/Underground-Cognitive-V0.3-test) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
slices: |
|
- sources: |
|
- model: TheHierophant/Underground-Cognitive-V0.3-test |
|
layer_range: [0, 16] |
|
parameters: |
|
attention: |
|
- filter: o_proj |
|
value: 1.1 |
|
- filter: q_proj |
|
value: 1.0 |
|
- filter: v_proj |
|
value: 1.0 |
|
- filter: down_proj |
|
value: 0.95 |
|
weight: 0.25 # Menor peso en capas primarias para una carga eficiente |
|
significance: 0.7 # Focalizar en patrones esenciales |
|
- sources: |
|
- model: TheHierophant/Underground-Cognitive-V0.3-test |
|
layer_range: [16, 32] |
|
parameters: |
|
attention: |
|
- filter: o_proj |
|
value: 1.3 |
|
- filter: q_proj |
|
value: 1.2 |
|
- filter: v_proj |
|
value: 1.15 |
|
- filter: down_proj |
|
value: 1.1 |
|
weight: 0.35 # Peso moderado para capas secundarias |
|
significance: 0.8 # Enfatizar la atenci贸n en informaci贸n relevante |
|
- sources: |
|
- model: TheHierophant/Underground-Cognitive-V0.3-test |
|
layer_range: [32, 48] |
|
parameters: |
|
attention: |
|
- filter: o_proj |
|
value: 1.7 |
|
- filter: q_proj |
|
value: 1.6 |
|
- filter: v_proj |
|
value: 1.5 |
|
- filter: down_proj |
|
value: 1.4 |
|
weight: 0.4 # Peso incrementado para aprovechar la potencia de las capas profundas |
|
significance: 0.9 # Enfocar la importancia en la atenci贸n profunda |
|
|
|
base_model_config: |
|
attention_bias: false |
|
attention_dropout: 0.05 # Mantener dropout bajo para evitar sobreajuste |
|
hidden_act: "silu" # Silu para una activaci贸n m谩s suave y eficiente |
|
hidden_size: 4096 |
|
initializer_range: 0.02 |
|
intermediate_size: 14336 |
|
max_position_embeddings: 4096 |
|
num_attention_heads: 32 |
|
num_hidden_layers: 48 |
|
num_key_value_heads: 8 |
|
pretraining_tp: 1 |
|
rms_norm_eps: 1e-05 |
|
rope_scaling: 1.3 # Ajuste simplificado para manejar la posici贸n |
|
rope_theta: 10000.0 |
|
tie_word_embeddings: true |
|
vocab_size: 32000 |
|
use_cache: true |
|
dtype: bfloat16 |
|
merge_method: passthrough |
|
``` |
|
|
