Update config.json
Browse files- config.json +9 -15
config.json
CHANGED
@@ -3,31 +3,25 @@
|
|
3 |
"Qwen2ForCausalLM"
|
4 |
],
|
5 |
"attention_dropout": 0.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
"max_position_embeddings": 32768,
|
7 |
"max_window_layers": 35,
|
8 |
"model_type": "qwen2",
|
9 |
"num_attention_heads": 40,
|
10 |
"num_hidden_layers": 40,
|
11 |
"num_key_value_heads": 40,
|
12 |
-
"number_rep_kv": 1,
|
13 |
-
|
14 |
-
"resid_pdrop": 0.0,
|
15 |
"rms_norm_eps": 1e-06,
|
16 |
-
"
|
17 |
-
"rope_theta": 10000.0,
|
18 |
-
"scan_attention_layers": false,
|
19 |
-
"scan_layers": true,
|
20 |
-
"scan_mlp_chunk_size": 1024,
|
21 |
-
"scan_ring_attention": false,
|
22 |
-
"shard_attention_computation": true,
|
23 |
"sliding_window": 32768,
|
24 |
"tie_word_embeddings": false,
|
25 |
-
"torch_dtype": "
|
26 |
-
"transformers_version": "4.
|
27 |
"use_cache": true,
|
28 |
-
"use_scan_mlp": false,
|
29 |
-
"use_sharded_kv_caching": true,
|
30 |
-
"use_sharding_constraint": false,
|
31 |
"use_sliding_window": false,
|
32 |
"vocab_size": 152064
|
33 |
}
|
|
|
3 |
"Qwen2ForCausalLM"
|
4 |
],
|
5 |
"attention_dropout": 0.0,
|
6 |
+
"bos_token_id": 151643,
|
7 |
+
"eos_token_id": 151645,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 5120,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 13696,
|
12 |
"max_position_embeddings": 32768,
|
13 |
"max_window_layers": 35,
|
14 |
"model_type": "qwen2",
|
15 |
"num_attention_heads": 40,
|
16 |
"num_hidden_layers": 40,
|
17 |
"num_key_value_heads": 40,
|
|
|
|
|
|
|
18 |
"rms_norm_eps": 1e-06,
|
19 |
+
"rope_theta": 1000000.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
"sliding_window": 32768,
|
21 |
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.37.0",
|
24 |
"use_cache": true,
|
|
|
|
|
|
|
25 |
"use_sliding_window": false,
|
26 |
"vocab_size": 152064
|
27 |
}
|