yukiontheiceberg
commited on
Commit
•
cf1a5cb
1
Parent(s):
ba79f4e
Upload config.json with huggingface_hub
Browse files- config.json +4 -4
config.json
CHANGED
@@ -11,8 +11,8 @@
|
|
11 |
"hidden_size": 8192,
|
12 |
"initializer_range": 0.02,
|
13 |
"intermediate_size": 22016,
|
14 |
-
"max_position_embeddings":
|
15 |
-
"max_sequence_length":
|
16 |
"model_type": "llama",
|
17 |
"num_attention_heads": 64,
|
18 |
"num_hidden_layers": 80,
|
@@ -21,10 +21,10 @@
|
|
21 |
"pretraining_tp": 1,
|
22 |
"rms_norm_eps": 1e-05,
|
23 |
"rope_scaling": null,
|
24 |
-
"rope_theta":
|
25 |
"tie_word_embeddings": false,
|
26 |
"torch_dtype": "float16",
|
27 |
"transformers_version": "4.39.3",
|
28 |
"use_cache": true,
|
29 |
"vocab_size": 32032
|
30 |
-
}
|
|
|
11 |
"hidden_size": 8192,
|
12 |
"initializer_range": 0.02,
|
13 |
"intermediate_size": 22016,
|
14 |
+
"max_position_embeddings": 2048,
|
15 |
+
"max_sequence_length": 2048,
|
16 |
"model_type": "llama",
|
17 |
"num_attention_heads": 64,
|
18 |
"num_hidden_layers": 80,
|
|
|
21 |
"pretraining_tp": 1,
|
22 |
"rms_norm_eps": 1e-05,
|
23 |
"rope_scaling": null,
|
24 |
+
"rope_theta": 10000.0,
|
25 |
"tie_word_embeddings": false,
|
26 |
"torch_dtype": "float16",
|
27 |
"transformers_version": "4.39.3",
|
28 |
"use_cache": true,
|
29 |
"vocab_size": 32032
|
30 |
+
}
|