Update config.json
Browse files- config.json +7 -8
config.json
CHANGED
@@ -7,19 +7,18 @@
|
|
7 |
"bos_token_id": 1,
|
8 |
"eos_token_id": 2,
|
9 |
"hidden_act": "silu",
|
10 |
-
"hidden_size":
|
11 |
"initializer_range": 0.02,
|
12 |
-
"intermediate_size":
|
13 |
-
"max_position_embeddings":
|
14 |
-
"mlp_bias": false,
|
15 |
"model_type": "llama",
|
16 |
-
"num_attention_heads":
|
17 |
-
"num_hidden_layers":
|
18 |
-
"num_key_value_heads":
|
19 |
"pretraining_tp": 1,
|
20 |
"rms_norm_eps": 1e-05,
|
21 |
"rope_scaling": null,
|
22 |
-
"rope_theta":
|
23 |
"tie_word_embeddings": false,
|
24 |
"torch_dtype": "bfloat16",
|
25 |
"transformers_version": "4.40.1",
|
|
|
7 |
"bos_token_id": 1,
|
8 |
"eos_token_id": 2,
|
9 |
"hidden_act": "silu",
|
10 |
+
"hidden_size": 5120,
|
11 |
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 13824,
|
13 |
+
"max_position_embeddings": 4096,
|
|
|
14 |
"model_type": "llama",
|
15 |
+
"num_attention_heads": 40,
|
16 |
+
"num_hidden_layers": 40,
|
17 |
+
"num_key_value_heads": 40,
|
18 |
"pretraining_tp": 1,
|
19 |
"rms_norm_eps": 1e-05,
|
20 |
"rope_scaling": null,
|
21 |
+
"rope_theta": 10000.0,
|
22 |
"tie_word_embeddings": false,
|
23 |
"torch_dtype": "bfloat16",
|
24 |
"transformers_version": "4.40.1",
|