upload model files
Browse files- config.json +42 -0
- static_query_weights.pt +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +25 -0
config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"document_chunk_length": 512,
|
| 10 |
+
"document_pooling": "max_log1p_relu",
|
| 11 |
+
"dtype": "float32",
|
| 12 |
+
"eos_token_id": null,
|
| 13 |
+
"gradient_checkpointing": false,
|
| 14 |
+
"hidden_act": "gelu",
|
| 15 |
+
"hidden_dropout_prob": 0.1,
|
| 16 |
+
"hidden_size": 768,
|
| 17 |
+
"inference_free_query": true,
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"is_decoder": false,
|
| 21 |
+
"layer_norm_eps": 1e-12,
|
| 22 |
+
"max_chunks_per_document": 2,
|
| 23 |
+
"max_position_embeddings": 512,
|
| 24 |
+
"model_type": "bert",
|
| 25 |
+
"num_attention_heads": 12,
|
| 26 |
+
"num_hidden_layers": 3,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"position_embedding_type": "absolute",
|
| 29 |
+
"pruned_from_checkpoint": "/vol/static_splade/numpy_pandas_pybind11_v1/checkpoints/splade_v3_doc_static_full_v3_stronger_flops/best_proxy",
|
| 30 |
+
"pruned_layer_indices": [
|
| 31 |
+
0,
|
| 32 |
+
6,
|
| 33 |
+
11
|
| 34 |
+
],
|
| 35 |
+
"query_encoder_type": "learned_static_token_weights",
|
| 36 |
+
"static_query_weight_file": "static_query_weights.pt",
|
| 37 |
+
"tie_word_embeddings": true,
|
| 38 |
+
"transformers_version": "5.13.1",
|
| 39 |
+
"type_vocab_size": 2,
|
| 40 |
+
"use_cache": true,
|
| 41 |
+
"vocab_size": 30522
|
| 42 |
+
}
|
static_query_weights.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4a12b4d85a612407f3dcc01760ae7c322cd693f8283988ec94d2ed60f4cda54
|
| 3 |
+
size 368790
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"cls_token": "[CLS]",
|
| 5 |
+
"do_basic_tokenize": true,
|
| 6 |
+
"do_lower_case": true,
|
| 7 |
+
"is_local": true,
|
| 8 |
+
"local_files_only": false,
|
| 9 |
+
"mask_token": "[MASK]",
|
| 10 |
+
"max_length": 128,
|
| 11 |
+
"model_max_length": 512,
|
| 12 |
+
"never_split": null,
|
| 13 |
+
"pad_to_multiple_of": null,
|
| 14 |
+
"pad_token": "[PAD]",
|
| 15 |
+
"pad_token_type_id": 0,
|
| 16 |
+
"padding_side": "right",
|
| 17 |
+
"sep_token": "[SEP]",
|
| 18 |
+
"stride": 0,
|
| 19 |
+
"strip_accents": null,
|
| 20 |
+
"tokenize_chinese_chars": true,
|
| 21 |
+
"tokenizer_class": "BertTokenizer",
|
| 22 |
+
"truncation_side": "right",
|
| 23 |
+
"truncation_strategy": "longest_first",
|
| 24 |
+
"unk_token": "[UNK]"
|
| 25 |
+
}
|