Update config.json
Browse files- config.json +18 -31
config.json
CHANGED
@@ -1,32 +1,19 @@
|
|
1 |
{
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
"
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
"
|
10 |
-
"
|
11 |
-
"
|
12 |
-
"
|
13 |
-
"
|
14 |
-
"
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
"hidden_size": 4544,
|
21 |
-
"initializer_range": 0.02,
|
22 |
-
"layer_norm_epsilon": 1e-05,
|
23 |
-
"model_type": "RefinedWebModel",
|
24 |
-
"multi_query": true,
|
25 |
-
"n_head": 71,
|
26 |
-
"n_layer": 32,
|
27 |
-
"parallel_attn": true,
|
28 |
-
"torch_dtype": "bfloat16",
|
29 |
-
"transformers_version": "4.27.4",
|
30 |
-
"use_cache": true,
|
31 |
-
"vocab_size": 65024
|
32 |
-
}
|
|
|
1 |
{
|
2 |
+
"architectures": ["LLaMAForCausalLM"],
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"hidden_act": "silu",
|
6 |
+
"hidden_size": 8192,
|
7 |
+
"intermediate_size": 22016,
|
8 |
+
"initializer_range": 0.02,
|
9 |
+
"max_sequence_length": 2048,
|
10 |
+
"model_type": "llama",
|
11 |
+
"num_attention_heads": 64,
|
12 |
+
"num_hidden_layers": 80,
|
13 |
+
"pad_token_id": 0,
|
14 |
+
"rms_norm_eps": 1e-05,
|
15 |
+
"torch_dtype": "float16",
|
16 |
+
"transformers_version": "4.28.0.dev0",
|
17 |
+
"use_cache": true,
|
18 |
+
"vocab_size": 32000
|
19 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|