Commit
•
0222ff7
1
Parent(s):
2391d55
Update config.json
Browse files- config.json +7 -5
config.json
CHANGED
|
@@ -11,16 +11,18 @@
|
|
| 11 |
"hidden_size": 4096,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"intermediate_size": 14336,
|
| 14 |
-
"hidden_size": 4096,
|
| 15 |
-
"initializer_range": 0.02,
|
| 16 |
-
"intermediate_size": 14336,
|
| 17 |
"max_position_embeddings": 1048576,
|
| 18 |
"model_type": "llama",
|
| 19 |
"num_attention_heads": 32,
|
| 20 |
"num_hidden_layers": 32,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
"tie_word_embeddings": false,
|
| 22 |
"torch_dtype": "bfloat16",
|
| 23 |
"transformers_version": "4.40.0.dev0",
|
| 24 |
-
"use_cache":
|
| 25 |
"vocab_size": 128256
|
| 26 |
-
}
|
|
|
|
| 11 |
"hidden_size": 4096,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"intermediate_size": 14336,
|
|
|
|
|
|
|
|
|
|
| 14 |
"max_position_embeddings": 1048576,
|
| 15 |
"model_type": "llama",
|
| 16 |
"num_attention_heads": 32,
|
| 17 |
"num_hidden_layers": 32,
|
| 18 |
+
"num_key_value_heads": 8,
|
| 19 |
+
"pretraining_tp": 1,
|
| 20 |
+
"rms_norm_eps": 1e-05,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 500000.0,
|
| 23 |
"tie_word_embeddings": false,
|
| 24 |
"torch_dtype": "bfloat16",
|
| 25 |
"transformers_version": "4.40.0.dev0",
|
| 26 |
+
"use_cache": false,
|
| 27 |
"vocab_size": 128256
|
| 28 |
+
}
|