Upload 2 files
Browse files- configuration_HelpingAI.py +60 -0
configuration_HelpingAI.py
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
""" HelpingAI model configuration"""
|
2 |
+
|
3 |
+
from transformers import PretrainedConfig
|
4 |
+
from transformers.utils import logging
|
5 |
+
|
6 |
+
|
7 |
+
logger = logging.get_logger(__name__)
|
8 |
+
|
9 |
+
class HelpingAIConfig(PretrainedConfig):
|
10 |
+
keys_to_ignore_at_inference = ["past_key_values"]
|
11 |
+
model_type = "HelpingAI"
|
12 |
+
def __init__(
|
13 |
+
self,
|
14 |
+
vocab_size=50304,
|
15 |
+
hidden_size=2560,
|
16 |
+
intermediate_size=6912,
|
17 |
+
num_hidden_layers=32,
|
18 |
+
num_attention_heads=32,
|
19 |
+
num_key_value_heads=32,
|
20 |
+
head_dim=256,
|
21 |
+
hidden_act="silu",
|
22 |
+
max_position_embeddings=4096,
|
23 |
+
initializer_range=0.02,
|
24 |
+
rms_norm_eps=1e-6,
|
25 |
+
use_cache=True,
|
26 |
+
hidden_activation=None,
|
27 |
+
rope_theta=10000,
|
28 |
+
rope_pct=0.25,
|
29 |
+
attention_bias=False,
|
30 |
+
attention_dropout=0.0,
|
31 |
+
num_experts_per_tok=2,
|
32 |
+
num_local_experts=8,
|
33 |
+
router_aux_loss_coef=0.02,
|
34 |
+
output_router_logits=False,
|
35 |
+
norm_eps=1.0e-5,
|
36 |
+
**kwargs,
|
37 |
+
):
|
38 |
+
self.vocab_size = vocab_size
|
39 |
+
self.max_position_embeddings = max_position_embeddings
|
40 |
+
self.hidden_size = hidden_size
|
41 |
+
self.intermediate_size = intermediate_size
|
42 |
+
self.num_hidden_layers = num_hidden_layers
|
43 |
+
self.num_attention_heads = num_attention_heads
|
44 |
+
self.head_dim = head_dim
|
45 |
+
self.hidden_act = hidden_act
|
46 |
+
self.hidden_activation = hidden_activation
|
47 |
+
self.num_key_value_heads = num_key_value_heads
|
48 |
+
self.initializer_range = initializer_range
|
49 |
+
self.rms_norm_eps = rms_norm_eps
|
50 |
+
self.use_cache = use_cache
|
51 |
+
self.rope_theta = rope_theta
|
52 |
+
self.attention_bias = attention_bias
|
53 |
+
self.attention_dropout = attention_dropout
|
54 |
+
self.num_experts_per_tok = num_experts_per_tok
|
55 |
+
self.num_local_experts = num_local_experts
|
56 |
+
self.router_aux_loss_coef = router_aux_loss_coef
|
57 |
+
self.output_router_logits = output_router_logits
|
58 |
+
self.rope_pct = rope_pct
|
59 |
+
self.norm_eps = norm_eps
|
60 |
+
super().__init__(**kwargs)
|