Upload config.json with huggingface_hub
Browse files- config.json +4 -4
config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"architectures": [
|
3 |
-
"
|
4 |
],
|
5 |
"attention_bias": false,
|
6 |
"attention_dropout": 0.0,
|
@@ -13,7 +13,7 @@
|
|
13 |
"intermediate_size": 17408,
|
14 |
"max_position_embeddings": 40960,
|
15 |
"max_window_layers": 40,
|
16 |
-
"model_type": "
|
17 |
"num_attention_heads": 40,
|
18 |
"num_hidden_layers": 1,
|
19 |
"num_key_value_heads": 8,
|
@@ -27,6 +27,6 @@
|
|
27 |
"use_cache": true,
|
28 |
"use_sliding_window": false,
|
29 |
"vocab_size": 151936,
|
30 |
-
"draft_vocab_size":
|
31 |
|
32 |
-
}
|
|
|
1 |
{
|
2 |
"architectures": [
|
3 |
+
"Qwen3ForCausalLM"
|
4 |
],
|
5 |
"attention_bias": false,
|
6 |
"attention_dropout": 0.0,
|
|
|
13 |
"intermediate_size": 17408,
|
14 |
"max_position_embeddings": 40960,
|
15 |
"max_window_layers": 40,
|
16 |
+
"model_type": "qwen3",
|
17 |
"num_attention_heads": 40,
|
18 |
"num_hidden_layers": 1,
|
19 |
"num_key_value_heads": 8,
|
|
|
27 |
"use_cache": true,
|
28 |
"use_sliding_window": false,
|
29 |
"vocab_size": 151936,
|
30 |
+
"draft_vocab_size": 32000
|
31 |
|
32 |
+
}
|