Commit
•
d96afbe
1
Parent(s):
63977b8
Upload tiny models for ReformerForSequenceClassification
Browse files- config.json +52 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +4 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +10 -0
config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ReformerForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_head_size": 64,
|
| 6 |
+
"attn_layers": [
|
| 7 |
+
"local",
|
| 8 |
+
"local",
|
| 9 |
+
"local",
|
| 10 |
+
"local"
|
| 11 |
+
],
|
| 12 |
+
"axial_norm_std": 1.0,
|
| 13 |
+
"axial_pos_embds": true,
|
| 14 |
+
"axial_pos_embds_dim": [
|
| 15 |
+
16,
|
| 16 |
+
16
|
| 17 |
+
],
|
| 18 |
+
"axial_pos_shape": [
|
| 19 |
+
4,
|
| 20 |
+
25
|
| 21 |
+
],
|
| 22 |
+
"chunk_size_lm_head": 0,
|
| 23 |
+
"classifier_dropout": null,
|
| 24 |
+
"eos_token_id": 2,
|
| 25 |
+
"feed_forward_size": 32,
|
| 26 |
+
"hash_seed": 0,
|
| 27 |
+
"hidden_act": "gelu",
|
| 28 |
+
"hidden_dropout_prob": 0.1,
|
| 29 |
+
"hidden_size": 32,
|
| 30 |
+
"initializer_range": 0.02,
|
| 31 |
+
"layer_norm_eps": 1e-12,
|
| 32 |
+
"local_attention_probs_dropout_prob": 0.1,
|
| 33 |
+
"local_attn_chunk_length": 4,
|
| 34 |
+
"local_num_chunks_after": 0,
|
| 35 |
+
"local_num_chunks_before": 1,
|
| 36 |
+
"lsh_attention_probs_dropout_prob": null,
|
| 37 |
+
"lsh_attn_chunk_length": null,
|
| 38 |
+
"lsh_num_chunks_after": null,
|
| 39 |
+
"lsh_num_chunks_before": null,
|
| 40 |
+
"max_position_embeddings": 100,
|
| 41 |
+
"model_type": "reformer",
|
| 42 |
+
"num_attention_heads": 2,
|
| 43 |
+
"num_buckets": null,
|
| 44 |
+
"num_hashes": 1,
|
| 45 |
+
"num_hidden_layers": 4,
|
| 46 |
+
"pad_token_id": 0,
|
| 47 |
+
"tie_word_embeddings": false,
|
| 48 |
+
"torch_dtype": "float32",
|
| 49 |
+
"transformers_version": "4.28.0.dev0",
|
| 50 |
+
"use_cache": true,
|
| 51 |
+
"vocab_size": 320
|
| 52 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af96abb46b631b4c0c7b697ccfb4048bd6d0773d7316fef472780e24ce66bfed
|
| 3 |
+
size 371188
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": "</s>",
|
| 3 |
+
"unk_token": "<unk>"
|
| 4 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14478412faa9cfe39a1a77ddf447f2466ae5eabc3d389d73e2444cf47001e260
|
| 3 |
+
size 241801
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [],
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"model_max_length": 100,
|
| 6 |
+
"sp_model_kwargs": {},
|
| 7 |
+
"special_tokens_map_file": null,
|
| 8 |
+
"tokenizer_class": "ReformerTokenizer",
|
| 9 |
+
"unk_token": "<unk>"
|
| 10 |
+
}
|