MerziaAdamjee
commited on
Commit
•
ac8c3f6
1
Parent(s):
6827533
Upload MixFormerSequentialForCausalLM
Browse files- config.json +35 -0
- generation_config.json +4 -0
- pytorch_model.bin +3 -0
config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/phi-1_5",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architecture": {
|
5 |
+
"block_cls": "parallel",
|
6 |
+
"mixer": {},
|
7 |
+
"mlp": {
|
8 |
+
"mlp_cls": "mlp"
|
9 |
+
}
|
10 |
+
},
|
11 |
+
"architectures": [
|
12 |
+
"MixFormerSequentialForCausalLM"
|
13 |
+
],
|
14 |
+
"auto_map": {
|
15 |
+
"AutoConfig": "microsoft/phi-1_5--configuration_mixformer_sequential.MixFormerSequentialConfig",
|
16 |
+
"AutoModelForCausalLM": "microsoft/phi-1_5--modeling_mixformer_sequential.MixFormerSequentialForCausalLM"
|
17 |
+
},
|
18 |
+
"embd_layer": "default",
|
19 |
+
"embd_pdrop": 0.0,
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"layer_norm_epsilon": 1e-05,
|
22 |
+
"model_type": "mixformer-sequential",
|
23 |
+
"n_embd": 2048,
|
24 |
+
"n_head": 32,
|
25 |
+
"n_inner": null,
|
26 |
+
"n_layer": 24,
|
27 |
+
"n_positions": 2048,
|
28 |
+
"phyagi_version": "0.0.4.dev",
|
29 |
+
"resid_pdrop": 0.0,
|
30 |
+
"rotary_dim": 32,
|
31 |
+
"tie_word_embeddings": false,
|
32 |
+
"torch_dtype": "float32",
|
33 |
+
"transformers_version": "4.33.2",
|
34 |
+
"vocab_size": 51200
|
35 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"transformers_version": "4.33.2"
|
4 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:905ffaa14916369166acdc752668185f9b58ef327043803aa782cda9e3f7a398
|
3 |
+
size 5673167489
|