c123ian commited on
Commit
e6c31a5
1 Parent(s): 57479a3

Upload MixFormerSequentialForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +26 -0
  2. generation_config.json +4 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/phi-1_5",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "MixFormerSequentialForCausalLM"
6
+ ],
7
+ "auto_map": {
8
+ "AutoConfig": "microsoft/phi-1_5--configuration_mixformer_sequential.MixFormerSequentialConfig",
9
+ "AutoModelForCausalLM": "microsoft/phi-1_5--modeling_mixformer_sequential.MixFormerSequentialForCausalLM"
10
+ },
11
+ "embd_pdrop": 0.0,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "mixformer-sequential",
15
+ "n_embd": 2048,
16
+ "n_head": 32,
17
+ "n_inner": null,
18
+ "n_layer": 24,
19
+ "n_positions": 2048,
20
+ "resid_pdrop": 0.0,
21
+ "rotary_dim": 32,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.33.0",
25
+ "vocab_size": 51200
26
+ }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.33.0"
4
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:486212e1842e20ce20746fa6e62f40df584b756d101e1b711bc80c1b3e0995cf
3
+ size 5673167489