Commit
•
b7066be
1
Parent(s):
ecedffb
Upload config
Browse files- config.json +6 -2
config.json
CHANGED
|
@@ -14,11 +14,15 @@
|
|
| 14 |
"model_type": "llama",
|
| 15 |
"num_attention_heads": 40,
|
| 16 |
"num_hidden_layers": 40,
|
|
|
|
| 17 |
"pad_token_id": 0,
|
|
|
|
| 18 |
"rms_norm_eps": 1e-06,
|
|
|
|
|
|
|
| 19 |
"tie_word_embeddings": false,
|
| 20 |
-
"torch_dtype": "
|
| 21 |
-
"transformers_version": "4.
|
| 22 |
"use_cache": false,
|
| 23 |
"vocab_size": 32000
|
| 24 |
}
|
|
|
|
| 14 |
"model_type": "llama",
|
| 15 |
"num_attention_heads": 40,
|
| 16 |
"num_hidden_layers": 40,
|
| 17 |
+
"num_key_value_heads": 40,
|
| 18 |
"pad_token_id": 0,
|
| 19 |
+
"pretraining_tp": 1,
|
| 20 |
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 10000.0,
|
| 23 |
"tie_word_embeddings": false,
|
| 24 |
+
"torch_dtype": "bfloat16",
|
| 25 |
+
"transformers_version": "4.33.1",
|
| 26 |
"use_cache": false,
|
| 27 |
"vocab_size": 32000
|
| 28 |
}
|