Enable inference performance mode by default
Browse files- config.json +1 -0
- configuration_neollm.py +0 -0
- modeling_neollm.py +0 -0
config.json
CHANGED
|
@@ -5,6 +5,7 @@
|
|
| 5 |
],
|
| 6 |
"attention_bias": false,
|
| 7 |
"attention_dropout": 0.1,
|
|
|
|
| 8 |
"attn_res_num_blocks": 4,
|
| 9 |
"auto_map": {
|
| 10 |
"AutoConfig": "configuration_neollm.NeoLLMConfig",
|
|
|
|
| 5 |
],
|
| 6 |
"attention_bias": false,
|
| 7 |
"attention_dropout": 0.1,
|
| 8 |
+
"allow_cache_numerical_drift": true,
|
| 9 |
"attn_res_num_blocks": 4,
|
| 10 |
"auto_map": {
|
| 11 |
"AutoConfig": "configuration_neollm.NeoLLMConfig",
|
configuration_neollm.py
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
modeling_neollm.py
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|