Text Generation
Transformers
PyTorch
TeleFLM
custom_code
jasonfang3900 commited on
Commit
6409fb7
1 Parent(s): 8179f60

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +33 -0
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attention_bias": false,
3
+ "attention_dropout": 0.0,
4
+ "auto_map": {
5
+ "AutoConfig": "configuration_teleflm.TeleFLMConfig",
6
+ "AutoModel": "modeling_teleflm.TeleFLMModel",
7
+ "AutoModelForCausalLM": "modeling_teleflm.TeleFLMForCausalLM"
8
+ },
9
+ "bos_token_id": 1,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 20480,
13
+ "initializer_range": 0.02,
14
+ "input_mult": 1.0,
15
+ "intermediate_size": 98304,
16
+ "max_position_embeddings": 4096,
17
+ "model_type": "TeleFLM",
18
+ "mup_scale_factor": 80.0,
19
+ "num_attention_heads": 160,
20
+ "num_hidden_layers": 140,
21
+ "num_key_value_heads": 160,
22
+ "output_mult": 2.0,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_scaling": null,
26
+ "rope_theta": 10000,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.40.2",
30
+ "use_cache": true,
31
+ "use_mup": true,
32
+ "vocab_size": 81920
33
+ }