shunxing1234 commited on
Commit
8527200
1 Parent(s): fd76ea6

Upload config.json

Browse files
Files changed (1) hide show
  1. config.json +40 -0
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_residual_connection_post_layernorm": false,
3
+ "architectures": [
4
+ "TelechatForCausalLM"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "configuration_telechat.TelechatConfig",
8
+ "AutoModelForCausalLM": "modeling_telechat.TelechatForCausalLM"
9
+ },
10
+ "attention_dropout": 0.0,
11
+ "attention_softmax_in_fp32": true,
12
+ "bias_dropout_fusion": true,
13
+ "bos_token_id": 1,
14
+ "eos_token_id": 2,
15
+ "hidden_dropout": 0.0,
16
+ "hidden_size": 8192,
17
+ "initializer_range": 0.02,
18
+ "layer_norm_epsilon": 1e-05,
19
+ "masked_softmax_fusion": true,
20
+ "model_type": "telechat",
21
+ "n_head": 64,
22
+ "n_inner": null,
23
+ "num_key_value_heads": 8,
24
+ "n_layer": 96,
25
+ "pad_token_id": 3,
26
+ "pretraining_tp": 2,
27
+ "skip_bias_add": false,
28
+ "skip_bias_add_qkv": false,
29
+ "slow_but_exact": false,
30
+ "unk_token_id": 0,
31
+ "use_cache": true,
32
+ "vocab_size": 131072,
33
+ "ffn_hidden_size": 40960,
34
+ "flash_attn":true,
35
+ "tie_word_embeddings":false,
36
+ "training_seqlen":8192,
37
+ "base_seqlen":8192,
38
+ "seq_length": 8192
39
+ }
40
+