Update config.json
Browse files- config.json +6 -3
config.json
CHANGED
@@ -1,4 +1,5 @@
|
|
1 |
{
|
|
|
2 |
"architectures": [
|
3 |
"LlamaForCausalLM"
|
4 |
],
|
@@ -8,15 +9,17 @@
|
|
8 |
"hidden_size": 5120,
|
9 |
"initializer_range": 0.02,
|
10 |
"intermediate_size": 13824,
|
11 |
-
"max_position_embeddings":
|
12 |
"model_type": "llama",
|
13 |
"num_attention_heads": 40,
|
14 |
"num_hidden_layers": 40,
|
15 |
-
"
|
|
|
16 |
"rms_norm_eps": 1e-05,
|
|
|
17 |
"tie_word_embeddings": false,
|
18 |
"torch_dtype": "float16",
|
19 |
-
"transformers_version": "4.
|
20 |
"use_cache": true,
|
21 |
"vocab_size": 32000
|
22 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": null,
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
|
|
9 |
"hidden_size": 5120,
|
10 |
"initializer_range": 0.02,
|
11 |
"intermediate_size": 13824,
|
12 |
+
"max_position_embeddings": 4096,
|
13 |
"model_type": "llama",
|
14 |
"num_attention_heads": 40,
|
15 |
"num_hidden_layers": 40,
|
16 |
+
"num_key_value_heads": 40,
|
17 |
+
"pretraining_tp": 1,
|
18 |
"rms_norm_eps": 1e-05,
|
19 |
+
"rope_scaling": null,
|
20 |
"tie_word_embeddings": false,
|
21 |
"torch_dtype": "float16",
|
22 |
+
"transformers_version": "4.31.0.dev0",
|
23 |
"use_cache": true,
|
24 |
"vocab_size": 32000
|
25 |
}
|