initial push of mega MLM checkpoint in HF classes
Browse files- config.json +43 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation": "silu",
|
| 3 |
+
"add_lm_hidden_dense_layer": false,
|
| 4 |
+
"add_token_type_embeddings": false,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"MegaForMaskedLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_activation": "softmax",
|
| 9 |
+
"attention_probs_dropout_prob": 0.1,
|
| 10 |
+
"bidirectional": true,
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"chunk_size": -1,
|
| 13 |
+
"classifier_dropout": null,
|
| 14 |
+
"dropout_prob": 0.1,
|
| 15 |
+
"ema_projection_size": 16,
|
| 16 |
+
"eos_token_id": 2,
|
| 17 |
+
"hidden_dropout_prob": 0.1,
|
| 18 |
+
"hidden_size": 128,
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 256,
|
| 21 |
+
"layer_norm_eps": 1e-12,
|
| 22 |
+
"max_positions": 10000,
|
| 23 |
+
"model_type": "mega",
|
| 24 |
+
"nffn_activation_dropout_prob": 0.0,
|
| 25 |
+
"nffn_hidden_size": 256,
|
| 26 |
+
"norm_affine": true,
|
| 27 |
+
"normalization_type": "scalenorm",
|
| 28 |
+
"normalize_before_ffn": true,
|
| 29 |
+
"normalize_before_mega": true,
|
| 30 |
+
"num_hidden_layers": 4,
|
| 31 |
+
"pad_token_id": 1,
|
| 32 |
+
"relative_positional_bias": "rotary",
|
| 33 |
+
"shared_representation_size": 64,
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.27.0.dev0",
|
| 36 |
+
"truncation": null,
|
| 37 |
+
"type_vocab_size": 2,
|
| 38 |
+
"use_cache": true,
|
| 39 |
+
"use_chunking": false,
|
| 40 |
+
"use_feature_dropout": false,
|
| 41 |
+
"use_normalized_ffn": true,
|
| 42 |
+
"vocab_size": 50265
|
| 43 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1fc7bf63d83a3037c1e3a351205a9b2b8511e677e84763dd4164c3ee2a053a07
|
| 3 |
+
size 29332412
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"errors": "replace",
|
| 7 |
+
"mask_token": "<mask>",
|
| 8 |
+
"model_max_length": 512,
|
| 9 |
+
"pad_token": "<pad>",
|
| 10 |
+
"sep_token": "</s>",
|
| 11 |
+
"special_tokens_map_file": null,
|
| 12 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 13 |
+
"trim_offsets": true,
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|