Contrastive continue-train (mined hard negatives)
Browse files- .gitattributes +1 -0
- README.md +16 -0
- config.json +30 -0
- model.safetensors +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +23 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
tags:
|
| 5 |
+
- embeddings
|
| 6 |
+
- information-retrieval
|
| 7 |
+
- ramana-maharshi
|
| 8 |
+
- contrastive-learning
|
| 9 |
+
base_model: intfloat/multilingual-e5-large
|
| 10 |
+
license: mit
|
| 11 |
+
pipeline_tag: sentence-similarity
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
# AtmicEmbedding (English query→passage)
|
| 15 |
+
|
| 16 |
+
Contrastive continue-training of v1 with mined hard negatives. Use `query: ` / `passage: ` prefixes + mean pooling + L2 normalize.
|
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"XLMRobertaModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 1024,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 4096,
|
| 16 |
+
"is_decoder": false,
|
| 17 |
+
"layer_norm_eps": 1e-05,
|
| 18 |
+
"max_position_embeddings": 514,
|
| 19 |
+
"model_type": "xlm-roberta",
|
| 20 |
+
"num_attention_heads": 16,
|
| 21 |
+
"num_hidden_layers": 24,
|
| 22 |
+
"output_past": true,
|
| 23 |
+
"pad_token_id": 1,
|
| 24 |
+
"position_embedding_type": "absolute",
|
| 25 |
+
"tie_word_embeddings": true,
|
| 26 |
+
"transformers_version": "5.7.0",
|
| 27 |
+
"type_vocab_size": 1,
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 250002
|
| 30 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a58d0782ccecfec2e84a2ccbbea9eeef4a5f9f52556b555dd765e94336bc11e4
|
| 3 |
+
size 2239607120
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3bcfa4538ee4c6ba9e6193f91db66bd7e7d2d1f29ae91368db579b285dd0b21c
|
| 3 |
+
size 16766208
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"clean_up_tokenization_spaces": true,
|
| 6 |
+
"cls_token": "<s>",
|
| 7 |
+
"eos_token": "</s>",
|
| 8 |
+
"is_local": false,
|
| 9 |
+
"local_files_only": false,
|
| 10 |
+
"mask_token": "<mask>",
|
| 11 |
+
"max_length": 512,
|
| 12 |
+
"model_max_length": 512,
|
| 13 |
+
"pad_to_multiple_of": null,
|
| 14 |
+
"pad_token": "<pad>",
|
| 15 |
+
"pad_token_type_id": 0,
|
| 16 |
+
"padding_side": "right",
|
| 17 |
+
"sep_token": "</s>",
|
| 18 |
+
"stride": 0,
|
| 19 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 20 |
+
"truncation_side": "right",
|
| 21 |
+
"truncation_strategy": "longest_first",
|
| 22 |
+
"unk_token": "<unk>"
|
| 23 |
+
}
|