ybelkada
commited on
Commit
·
506ffae
1
Parent(s):
418ce69
add model weights
Browse files
config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_router_probs": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"SwitchTransformersForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 4096,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 1024,
|
| 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": 24,
|
| 22 |
+
"num_experts": 128,
|
| 23 |
+
"num_heads": 16,
|
| 24 |
+
"num_layers": 24,
|
| 25 |
+
"num_sparse_decoder_layers": 12,
|
| 26 |
+
"num_sparse_encoder_layers": 12,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"relative_attention_max_distance": 128,
|
| 29 |
+
"relative_attention_num_buckets": 32,
|
| 30 |
+
"router_aux_loss_coef": 0.001,
|
| 31 |
+
"router_bias": false,
|
| 32 |
+
"router_dtype": "float32",
|
| 33 |
+
"router_ignore_padding_tokens": false,
|
| 34 |
+
"router_jitter_noise": 0.01,
|
| 35 |
+
"router_type": "tokens_masked",
|
| 36 |
+
"router_z_loss_coef": 0.001,
|
| 37 |
+
"torch_dtype": "bfloat16",
|
| 38 |
+
"transformers_version": "4.25.0.dev0",
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 32128
|
| 41 |
+
}
|
pytorch_model-00001-of-00006.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bfc793680d0712c6cc132b1526b58cc43944fca41bc42b3af6b4ee815e8a20b9
|
| 3 |
+
size 9932574409
|
pytorch_model-00002-of-00006.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5b295b6fa51d9cda79d6cad4a3a0739495c3cafbdca6361b7628561c90bdc81
|
| 3 |
+
size 9992612399
|
pytorch_model-00003-of-00006.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0977b44b1f5455b5396f30ea1912ecba25e976222959b77120127958c2546f0e
|
| 3 |
+
size 9999431066
|
pytorch_model-00004-of-00006.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0ae9d9a02ff22fbf6a533aee5345a901eddd0fe3432a980568f04405c74451e
|
| 3 |
+
size 9992645539
|
pytorch_model-00005-of-00006.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9cf92961223faf5b9a26f38575dd76fdf72b92ed381d6445e64c1fe88d7a5c9
|
| 3 |
+
size 9992365526
|
pytorch_model-00006-of-00006.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac4788c061641b47c7e7e6f4eafd83d6d92cf1317abc6ebfec5b5949ab22cfb7
|
| 3 |
+
size 2842823871
|
pytorch_model.bin.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|