syx
commited on
Commit
·
f94ad98
1
Parent(s):
8f55951
turbo
Browse files- config.json +2 -2
- modeling_supersparsemixtral.py +1 -1
config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
-
"
|
| 4 |
],
|
| 5 |
"auto_map": {
|
| 6 |
"AutoConfig": "configuration_supersparsemixtral.SuperSparseMixtralConfig",
|
|
@@ -15,7 +15,7 @@
|
|
| 15 |
"initializer_range": 0.02,
|
| 16 |
"intermediate_size": 14336,
|
| 17 |
"max_position_embeddings": 32768,
|
| 18 |
-
"model_type": "
|
| 19 |
"num_attention_heads": 32,
|
| 20 |
"num_experts_per_tok": 2,
|
| 21 |
"num_hidden_layers": 32,
|
|
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
+
"TurboSparseMixtralForCausalLM"
|
| 4 |
],
|
| 5 |
"auto_map": {
|
| 6 |
"AutoConfig": "configuration_supersparsemixtral.SuperSparseMixtralConfig",
|
|
|
|
| 15 |
"initializer_range": 0.02,
|
| 16 |
"intermediate_size": 14336,
|
| 17 |
"max_position_embeddings": 32768,
|
| 18 |
+
"model_type": "trubosparsemixtral",
|
| 19 |
"num_attention_heads": 32,
|
| 20 |
"num_experts_per_tok": 2,
|
| 21 |
"num_hidden_layers": 32,
|
modeling_supersparsemixtral.py
CHANGED
|
@@ -541,7 +541,7 @@ if is_torch_fx_available():
|
|
| 541 |
|
| 542 |
logger = logging.get_logger(__name__)
|
| 543 |
|
| 544 |
-
_CONFIG_FOR_DOC = "
|
| 545 |
|
| 546 |
|
| 547 |
def load_balancing_loss_func(
|
|
|
|
| 541 |
|
| 542 |
logger = logging.get_logger(__name__)
|
| 543 |
|
| 544 |
+
_CONFIG_FOR_DOC = "TurboSparseMixtralConfig"
|
| 545 |
|
| 546 |
|
| 547 |
def load_balancing_loss_func(
|