Update config.json
Browse files- config.json +10 -14
config.json
CHANGED
@@ -5,35 +5,31 @@
|
|
5 |
"attention_bias": false,
|
6 |
"attention_dropout": 0.0,
|
7 |
"bos_token_id": 128000,
|
8 |
-
"eos_token_id":
|
9 |
-
|
10 |
-
128008,
|
11 |
-
128009
|
12 |
-
],
|
13 |
-
"head_dim": 128,
|
14 |
"hidden_act": "silu",
|
15 |
-
"hidden_size":
|
16 |
"initializer_range": 0.02,
|
17 |
-
"intermediate_size":
|
18 |
"max_position_embeddings": 131072,
|
19 |
"mlp_bias": false,
|
20 |
"model_type": "llama",
|
21 |
-
"num_attention_heads":
|
22 |
-
"num_hidden_layers":
|
23 |
"num_key_value_heads": 8,
|
24 |
"pretraining_tp": 1,
|
25 |
"rms_norm_eps": 1e-05,
|
26 |
"rope_scaling": {
|
27 |
-
"factor":
|
28 |
"high_freq_factor": 4.0,
|
29 |
"low_freq_factor": 1.0,
|
30 |
"original_max_position_embeddings": 8192,
|
31 |
"rope_type": "llama3"
|
32 |
},
|
33 |
"rope_theta": 500000.0,
|
34 |
-
"tie_word_embeddings":
|
35 |
"torch_dtype": "bfloat16",
|
36 |
-
"transformers_version": "4.
|
37 |
"use_cache": true,
|
38 |
"vocab_size": 128256
|
39 |
-
}
|
|
|
5 |
"attention_bias": false,
|
6 |
"attention_dropout": 0.0,
|
7 |
"bos_token_id": 128000,
|
8 |
+
"eos_token_id": 128001,
|
9 |
+
"head_dim": 64,
|
|
|
|
|
|
|
|
|
10 |
"hidden_act": "silu",
|
11 |
+
"hidden_size": 2048,
|
12 |
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 8192,
|
14 |
"max_position_embeddings": 131072,
|
15 |
"mlp_bias": false,
|
16 |
"model_type": "llama",
|
17 |
+
"num_attention_heads": 32,
|
18 |
+
"num_hidden_layers": 16,
|
19 |
"num_key_value_heads": 8,
|
20 |
"pretraining_tp": 1,
|
21 |
"rms_norm_eps": 1e-05,
|
22 |
"rope_scaling": {
|
23 |
+
"factor": 32.0,
|
24 |
"high_freq_factor": 4.0,
|
25 |
"low_freq_factor": 1.0,
|
26 |
"original_max_position_embeddings": 8192,
|
27 |
"rope_type": "llama3"
|
28 |
},
|
29 |
"rope_theta": 500000.0,
|
30 |
+
"tie_word_embeddings": true,
|
31 |
"torch_dtype": "bfloat16",
|
32 |
+
"transformers_version": "4.45.0.dev0",
|
33 |
"use_cache": true,
|
34 |
"vocab_size": 128256
|
35 |
+
}
|