Upload config.json with huggingface_hub
Browse files- config.json +7 -2
config.json
CHANGED
@@ -1,8 +1,9 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
|
|
6 |
"bos_token_id": 1,
|
7 |
"eos_token_id": 2,
|
8 |
"hidden_act": "silu",
|
@@ -13,11 +14,15 @@
|
|
13 |
"model_type": "llama",
|
14 |
"num_attention_heads": 40,
|
15 |
"num_hidden_layers": 40,
|
|
|
16 |
"pad_token_id": 0,
|
|
|
17 |
"rms_norm_eps": 1e-06,
|
|
|
|
|
18 |
"tie_word_embeddings": false,
|
19 |
"torch_dtype": "float16",
|
20 |
-
"transformers_version": "4.
|
21 |
"use_cache": true,
|
22 |
"vocab_size": 32000
|
23 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "lmsys/vicuna-13b-v1.3",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
+
"attention_bias": false,
|
7 |
"bos_token_id": 1,
|
8 |
"eos_token_id": 2,
|
9 |
"hidden_act": "silu",
|
|
|
14 |
"model_type": "llama",
|
15 |
"num_attention_heads": 40,
|
16 |
"num_hidden_layers": 40,
|
17 |
+
"num_key_value_heads": 40,
|
18 |
"pad_token_id": 0,
|
19 |
+
"pretraining_tp": 1,
|
20 |
"rms_norm_eps": 1e-06,
|
21 |
+
"rope_scaling": null,
|
22 |
+
"rope_theta": 10000.0,
|
23 |
"tie_word_embeddings": false,
|
24 |
"torch_dtype": "float16",
|
25 |
+
"transformers_version": "4.34.0.dev0",
|
26 |
"use_cache": true,
|
27 |
"vocab_size": 32000
|
28 |
}
|