matthewkenney commited on
Commit
dff68b0
1 Parent(s): 35bd735

Upload MixFormerSequentialForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +30 -0
  2. generation_config.json +4 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/phi-1_5",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "MixFormerSequentialForCausalLM"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "microsoft/phi-1_5--configuration_mixformer_sequential.MixFormerSequentialConfig",
10
+ "AutoModelForCausalLM": "microsoft/phi-1_5--modeling_mixformer_sequential.MixFormerSequentialForCausalLM"
11
+ },
12
+ "embd_pdrop": 0.0,
13
+ "flash_rotary": false,
14
+ "fused_dense": false,
15
+ "initializer_range": 0.02,
16
+ "layer_norm_epsilon": 1e-05,
17
+ "model_type": "mixformer-sequential",
18
+ "n_embd": 2048,
19
+ "n_head": 32,
20
+ "n_head_kv": null,
21
+ "n_inner": null,
22
+ "n_layer": 24,
23
+ "n_positions": 2048,
24
+ "resid_pdrop": 0.0,
25
+ "rotary_dim": 32,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "float16",
28
+ "transformers_version": "4.35.2",
29
+ "vocab_size": 51200
30
+ }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.35.2"
4
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d6d37781b320405bce673e7e52b95977d5becc79bd3ae434bb0b64bc760f9c3
3
+ size 2836565464