ybelkada
commited on
Commit
•
a5889f0
1
Parent(s):
36fa7a8
add model weights
Browse files- config.json +42 -0
- pytorch_model-00001-of-00003.bin +3 -0
- pytorch_model-00002-of-00003.bin +3 -0
- pytorch_model-00003-of-00003.bin +3 -0
- pytorch_model.bin.index.json +0 -0
config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_router_probs": false,
|
3 |
+
"architectures": [
|
4 |
+
"SwitchTransformersForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 3072,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 768,
|
9 |
+
"decoder_sparse_step": 2,
|
10 |
+
"dense_act_fn": "relu",
|
11 |
+
"dropout_rate": 0.1,
|
12 |
+
"encoder_sparse_step": 2,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"expert_capacity": 64,
|
15 |
+
"feed_forward_proj": "relu",
|
16 |
+
"initializer_factor": 1.0,
|
17 |
+
"is_encoder_decoder": true,
|
18 |
+
"is_gated_act": false,
|
19 |
+
"layer_norm_epsilon": 1e-06,
|
20 |
+
"model_type": "switch_transformers",
|
21 |
+
"num_decoder_layers": 12,
|
22 |
+
"num_experts": 128,
|
23 |
+
"num_heads": 12,
|
24 |
+
"num_layers": 12,
|
25 |
+
"num_selected_experts": 1,
|
26 |
+
"num_sparse_decoder_layers": 6,
|
27 |
+
"num_sparse_encoder_layers": 6,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"relative_attention_max_distance": 128,
|
30 |
+
"relative_attention_num_buckets": 32,
|
31 |
+
"router_aux_loss_coef": 0.001,
|
32 |
+
"router_bias": false,
|
33 |
+
"router_dtype": "float32",
|
34 |
+
"router_ignore_padding_tokens": false,
|
35 |
+
"router_jitter_noise": 0.01,
|
36 |
+
"router_type": "tokens_masked",
|
37 |
+
"router_z_loss_coef": 0.001,
|
38 |
+
"torch_dtype": "float32",
|
39 |
+
"transformers_version": "4.25.0.dev0",
|
40 |
+
"use_cache": true,
|
41 |
+
"vocab_size": 32128
|
42 |
+
}
|
pytorch_model-00001-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:828943851336b5f9996086dafbf65495acc2e0b3a6d05134d26418fde560e69e
|
3 |
+
size 9896485994
|
pytorch_model-00002-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d892df447c7fe20404835a366a1170d374b586a48acbf243b37a7f3ae0b457e
|
3 |
+
size 10000335528
|
pytorch_model-00003-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14287b378d085d3fa5958e6521f90708d2b39ca3bf4e611058dc786ae3472995
|
3 |
+
size 9962580266
|
pytorch_model.bin.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|