Upload MT5ForConditionalGeneration
Browse files- config.json +101 -0
- generation_config.json +7 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/mt5-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MT5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 2048,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 768,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "gelu_new",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"eos_token_id": 1,
|
| 13 |
+
"feed_forward_proj": "gated-gelu",
|
| 14 |
+
"initializer_factor": 1.0,
|
| 15 |
+
"is_encoder_decoder": true,
|
| 16 |
+
"is_gated_act": true,
|
| 17 |
+
"label2id": {
|
| 18 |
+
"nc": {
|
| 19 |
+
"autos": 9.0,
|
| 20 |
+
"entertainment": 6.0,
|
| 21 |
+
"finance": 3.0,
|
| 22 |
+
"foodanddrink": 0.0,
|
| 23 |
+
"health": 7.0,
|
| 24 |
+
"lifestyle": 4.0,
|
| 25 |
+
"news": 5.0,
|
| 26 |
+
"sports": 1.0,
|
| 27 |
+
"travel": 2.0,
|
| 28 |
+
"video": 8.0
|
| 29 |
+
},
|
| 30 |
+
"paws-x": {
|
| 31 |
+
"different": 0.0,
|
| 32 |
+
"same": 1.0
|
| 33 |
+
},
|
| 34 |
+
"qadsm": {
|
| 35 |
+
"Bad": 0.0,
|
| 36 |
+
"Good": 1.0
|
| 37 |
+
},
|
| 38 |
+
"qam": {
|
| 39 |
+
"False": 0.0,
|
| 40 |
+
"True": 1.0
|
| 41 |
+
},
|
| 42 |
+
"wpr": {
|
| 43 |
+
"Bad": 0.0,
|
| 44 |
+
"Excellent": 3.0,
|
| 45 |
+
"Fair": 1.0,
|
| 46 |
+
"Good": 2.0,
|
| 47 |
+
"Perfect": 4.0
|
| 48 |
+
},
|
| 49 |
+
"xnli": {
|
| 50 |
+
"contradiction": 2.0,
|
| 51 |
+
"entailment": 0.0,
|
| 52 |
+
"neutral": 1.0
|
| 53 |
+
}
|
| 54 |
+
},
|
| 55 |
+
"layer_norm_epsilon": 1e-06,
|
| 56 |
+
"model_type": "mt5",
|
| 57 |
+
"num_accum_batches": 4,
|
| 58 |
+
"num_decoder_layers": 12,
|
| 59 |
+
"num_heads": 12,
|
| 60 |
+
"num_layers": 12,
|
| 61 |
+
"output_past": true,
|
| 62 |
+
"pad_token_id": 0,
|
| 63 |
+
"r3f": true,
|
| 64 |
+
"r4f": false,
|
| 65 |
+
"relative_attention_max_distance": 128,
|
| 66 |
+
"relative_attention_num_buckets": 32,
|
| 67 |
+
"retain_gradients": false,
|
| 68 |
+
"scale_loss": true,
|
| 69 |
+
"tasks": [
|
| 70 |
+
[
|
| 71 |
+
"xnli",
|
| 72 |
+
3
|
| 73 |
+
],
|
| 74 |
+
[
|
| 75 |
+
"paws-x",
|
| 76 |
+
2
|
| 77 |
+
],
|
| 78 |
+
[
|
| 79 |
+
"nc",
|
| 80 |
+
10
|
| 81 |
+
],
|
| 82 |
+
[
|
| 83 |
+
"qadsm",
|
| 84 |
+
2
|
| 85 |
+
],
|
| 86 |
+
[
|
| 87 |
+
"wpr",
|
| 88 |
+
5
|
| 89 |
+
],
|
| 90 |
+
[
|
| 91 |
+
"qam",
|
| 92 |
+
2
|
| 93 |
+
]
|
| 94 |
+
],
|
| 95 |
+
"tie_word_embeddings": false,
|
| 96 |
+
"tokenizer_class": "T5Tokenizer",
|
| 97 |
+
"torch_dtype": "float32",
|
| 98 |
+
"transformers_version": "4.28.1",
|
| 99 |
+
"use_cache": true,
|
| 100 |
+
"vocab_size": 250112
|
| 101 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.28.1"
|
| 7 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc4d3305f0fcea25a4e7aafdd464e56e7885a476509ab7b3e73abb9c5f6e8d3c
|
| 3 |
+
size 2329698485
|