Create configuration_theta.py python Copy Edit
Browse files
configuration_theta.py python Copy Edit
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from transformers import PretrainedConfig
|
| 2 |
+
|
| 3 |
+
class ThetaConfig(PretrainedConfig):
|
| 4 |
+
model_type = "theta"
|
| 5 |
+
|
| 6 |
+
def __init__(
|
| 7 |
+
self,
|
| 8 |
+
vocab_size=32000,
|
| 9 |
+
hidden_size=4096,
|
| 10 |
+
intermediate_size=11008,
|
| 11 |
+
num_hidden_layers=32,
|
| 12 |
+
num_attention_heads=32,
|
| 13 |
+
hidden_act="silu",
|
| 14 |
+
max_position_embeddings=2048,
|
| 15 |
+
initializer_range=0.02,
|
| 16 |
+
rms_norm_eps=1e-5,
|
| 17 |
+
use_cache=True,
|
| 18 |
+
**kwargs,
|
| 19 |
+
):
|
| 20 |
+
super().__init__(**kwargs)
|
| 21 |
+
self.vocab_size = vocab_size
|
| 22 |
+
self.hidden_size = hidden_size
|
| 23 |
+
self.intermediate_size = intermediate_size
|
| 24 |
+
self.num_hidden_layers = num_hidden_layers
|
| 25 |
+
self.num_attention_heads = num_attention_heads
|
| 26 |
+
self.hidden_act = hidden_act
|
| 27 |
+
self.max_position_embeddings = max_position_embeddings
|
| 28 |
+
self.initializer_range = initializer_range
|
| 29 |
+
self.rms_norm_eps = rms_norm_eps
|
| 30 |
+
self.use_cache = use_cache
|