Make `config.json` compatible with standard sliding window config (#6)
Browse files- Make `config.json` compatible with standard sliding window config (9ccce627d4de65cc076eb0feb52c41cc43abde73)
Co-authored-by: Harry Mellor <[email protected]>
- config.json +6 -0
config.json
CHANGED
|
@@ -26,6 +26,12 @@
|
|
| 26 |
"num_key_value_heads": 20,
|
| 27 |
"resid_pdrop": 0.0,
|
| 28 |
"sliding_window": 512,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
"torch_dtype": "bfloat16",
|
| 30 |
"tie_word_embeddings": true,
|
| 31 |
"transformers_version": "4.46.1",
|
|
|
|
| 26 |
"num_key_value_heads": 20,
|
| 27 |
"resid_pdrop": 0.0,
|
| 28 |
"sliding_window": 512,
|
| 29 |
+
"layer_types": [
|
| 30 |
+
"full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention",
|
| 31 |
+
"full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention",
|
| 32 |
+
"full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention",
|
| 33 |
+
"full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention"
|
| 34 |
+
],
|
| 35 |
"torch_dtype": "bfloat16",
|
| 36 |
"tie_word_embeddings": true,
|
| 37 |
"transformers_version": "4.46.1",
|