New intent classification engine - MiniLM L6v2 and MiniLM L12v2 ONNX
This commit is contained in:
Priler
parent
4815c7f9bb
commit
8e830334e8
25 changed files with 61932 additions and 150 deletions
35
resources/models/all-MiniLM-L6-v2/.gitattributes
vendored
Normal file
35
resources/models/all-MiniLM-L6-v2/.gitattributes
vendored
Normal file
|
|
@ -0,0 +1,35 @@
|
|||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
35
resources/models/all-MiniLM-L6-v2/README.md
Normal file
35
resources/models/all-MiniLM-L6-v2/README.md
Normal file
|
|
@ -0,0 +1,35 @@
|
|||
---
|
||||
license: apache-2.0
|
||||
pipeline_tag: sentence-similarity
|
||||
---
|
||||
|
||||
ONNX port of [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) for text classification and similarity searches.
|
||||
|
||||
### Usage
|
||||
|
||||
Here's an example of performing inference using the model with [FastEmbed](https://github.com/qdrant/fastembed).
|
||||
|
||||
```py
|
||||
from fastembed import TextEmbedding
|
||||
|
||||
documents = [
|
||||
"You should stay, study and sprint.",
|
||||
"History can only prepare us to be surprised yet again.",
|
||||
]
|
||||
|
||||
model = TextEmbedding(model_name="sentence-transformers/all-MiniLM-L6-v2")
|
||||
embeddings = list(model.embed(documents))
|
||||
|
||||
# [
|
||||
# array([
|
||||
# 0.00611658, 0.00068912, -0.0203846, ..., -0.01751488, -0.01174267,
|
||||
# 0.01463472
|
||||
# ],
|
||||
# dtype=float32),
|
||||
# array([
|
||||
# 0.00173448, -0.00329958, 0.01557874, ..., -0.01473586, 0.0281806,
|
||||
# -0.00448205
|
||||
# ],
|
||||
# dtype=float32)
|
||||
# ]
|
||||
```
|
||||
25
resources/models/all-MiniLM-L6-v2/config.json
Normal file
25
resources/models/all-MiniLM-L6-v2/config.json
Normal file
|
|
@ -0,0 +1,25 @@
|
|||
{
|
||||
"_name_or_path": "sentence-transformers/all-MiniLM-L6-v2",
|
||||
"architectures": [
|
||||
"BertModel"
|
||||
],
|
||||
"attention_probs_dropout_prob": 0.1,
|
||||
"classifier_dropout": null,
|
||||
"gradient_checkpointing": false,
|
||||
"hidden_act": "gelu",
|
||||
"hidden_dropout_prob": 0.1,
|
||||
"hidden_size": 384,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 1536,
|
||||
"layer_norm_eps": 1e-12,
|
||||
"max_position_embeddings": 512,
|
||||
"model_type": "bert",
|
||||
"num_attention_heads": 12,
|
||||
"num_hidden_layers": 6,
|
||||
"pad_token_id": 0,
|
||||
"position_embedding_type": "absolute",
|
||||
"transformers_version": "4.36.2",
|
||||
"type_vocab_size": 2,
|
||||
"use_cache": true,
|
||||
"vocab_size": 30522
|
||||
}
|
||||
BIN
resources/models/all-MiniLM-L6-v2/model.onnx
(Stored with Git LFS)
Normal file
BIN
resources/models/all-MiniLM-L6-v2/model.onnx
(Stored with Git LFS)
Normal file
Binary file not shown.
37
resources/models/all-MiniLM-L6-v2/special_tokens_map.json
Normal file
37
resources/models/all-MiniLM-L6-v2/special_tokens_map.json
Normal file
|
|
@ -0,0 +1,37 @@
|
|||
{
|
||||
"cls_token": {
|
||||
"content": "[CLS]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"mask_token": {
|
||||
"content": "[MASK]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "[PAD]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"sep_token": {
|
||||
"content": "[SEP]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "[UNK]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
30686
resources/models/all-MiniLM-L6-v2/tokenizer.json
Normal file
30686
resources/models/all-MiniLM-L6-v2/tokenizer.json
Normal file
File diff suppressed because it is too large
Load diff
64
resources/models/all-MiniLM-L6-v2/tokenizer_config.json
Normal file
64
resources/models/all-MiniLM-L6-v2/tokenizer_config.json
Normal file
|
|
@ -0,0 +1,64 @@
|
|||
{
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "[PAD]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"100": {
|
||||
"content": "[UNK]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"101": {
|
||||
"content": "[CLS]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"102": {
|
||||
"content": "[SEP]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"103": {
|
||||
"content": "[MASK]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"cls_token": "[CLS]",
|
||||
"do_basic_tokenize": true,
|
||||
"do_lower_case": true,
|
||||
"mask_token": "[MASK]",
|
||||
"max_length": 128,
|
||||
"model_max_length": 512,
|
||||
"never_split": null,
|
||||
"pad_to_multiple_of": null,
|
||||
"pad_token": "[PAD]",
|
||||
"pad_token_type_id": 0,
|
||||
"padding_side": "right",
|
||||
"sep_token": "[SEP]",
|
||||
"stride": 0,
|
||||
"strip_accents": null,
|
||||
"tokenize_chinese_chars": true,
|
||||
"tokenizer_class": "BertTokenizer",
|
||||
"truncation_side": "right",
|
||||
"truncation_strategy": "longest_first",
|
||||
"unk_token": "[UNK]"
|
||||
}
|
||||
30522
resources/models/all-MiniLM-L6-v2/vocab.txt
Normal file
30522
resources/models/all-MiniLM-L6-v2/vocab.txt
Normal file
File diff suppressed because it is too large
Load diff
37
resources/models/paraphrase-multilingual-MiniLM-L12-v2-onnx-Q/.gitattributes
vendored
Normal file
37
resources/models/paraphrase-multilingual-MiniLM-L12-v2-onnx-Q/.gitattributes
vendored
Normal file
|
|
@ -0,0 +1,37 @@
|
|||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
unigram.json filter=lfs diff=lfs merge=lfs -text
|
||||
|
|
@ -0,0 +1,27 @@
|
|||
---
|
||||
license: apache-2.0
|
||||
pipeline_tag: sentence-similarity
|
||||
---
|
||||
|
||||
Quantized ONNX port of [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) for text classification and similarity searches.
|
||||
|
||||
### Usage
|
||||
|
||||
Here's an example of performing inference using the model with [FastEmbed](https://github.com/qdrant/fastembed).
|
||||
|
||||
```py
|
||||
from fastembed import TextEmbedding
|
||||
|
||||
documents = [
|
||||
"You should stay, study and sprint.",
|
||||
"History can only prepare us to be surprised yet again.",
|
||||
]
|
||||
|
||||
model = TextEmbedding(model_name="sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2")
|
||||
embeddings = list(model.embed(documents))
|
||||
|
||||
# [
|
||||
# array([1.96449570e-02, 1.60677675e-02, 4.10149433e-02...]),
|
||||
# array([-1.56669170e-02, -1.66313536e-02, -6.84525725e-03...])
|
||||
# ]
|
||||
```
|
||||
|
|
@ -0,0 +1,25 @@
|
|||
{
|
||||
"_name_or_path": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
|
||||
"architectures": [
|
||||
"BertModel"
|
||||
],
|
||||
"attention_probs_dropout_prob": 0.1,
|
||||
"classifier_dropout": null,
|
||||
"gradient_checkpointing": false,
|
||||
"hidden_act": "gelu",
|
||||
"hidden_dropout_prob": 0.1,
|
||||
"hidden_size": 384,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 1536,
|
||||
"layer_norm_eps": 1e-12,
|
||||
"max_position_embeddings": 512,
|
||||
"model_type": "bert",
|
||||
"num_attention_heads": 12,
|
||||
"num_hidden_layers": 12,
|
||||
"pad_token_id": 0,
|
||||
"position_embedding_type": "absolute",
|
||||
"transformers_version": "4.36.2",
|
||||
"type_vocab_size": 2,
|
||||
"use_cache": true,
|
||||
"vocab_size": 250037
|
||||
}
|
||||
BIN
resources/models/paraphrase-multilingual-MiniLM-L12-v2-onnx-Q/model_optimized.onnx
(Stored with Git LFS)
Normal file
BIN
resources/models/paraphrase-multilingual-MiniLM-L12-v2-onnx-Q/model_optimized.onnx
(Stored with Git LFS)
Normal file
Binary file not shown.
|
|
@ -0,0 +1,39 @@
|
|||
{
|
||||
"one_external_file": true,
|
||||
"opset": null,
|
||||
"optimization": {
|
||||
"disable_attention": null,
|
||||
"disable_attention_fusion": false,
|
||||
"disable_bias_gelu": null,
|
||||
"disable_bias_gelu_fusion": false,
|
||||
"disable_bias_skip_layer_norm": null,
|
||||
"disable_bias_skip_layer_norm_fusion": false,
|
||||
"disable_embed_layer_norm": true,
|
||||
"disable_embed_layer_norm_fusion": true,
|
||||
"disable_gelu": null,
|
||||
"disable_gelu_fusion": false,
|
||||
"disable_group_norm_fusion": true,
|
||||
"disable_layer_norm": null,
|
||||
"disable_layer_norm_fusion": false,
|
||||
"disable_packed_kv": true,
|
||||
"disable_rotary_embeddings": false,
|
||||
"disable_shape_inference": false,
|
||||
"disable_skip_layer_norm": null,
|
||||
"disable_skip_layer_norm_fusion": false,
|
||||
"enable_gelu_approximation": true,
|
||||
"enable_gemm_fast_gelu_fusion": false,
|
||||
"enable_transformers_specific_optimizations": true,
|
||||
"fp16": true,
|
||||
"no_attention_mask": false,
|
||||
"optimization_level": 2,
|
||||
"optimize_for_gpu": true,
|
||||
"optimize_with_onnxruntime_only": null,
|
||||
"use_mask_index": false,
|
||||
"use_multi_head_attention": false,
|
||||
"use_raw_attention_mask": false
|
||||
},
|
||||
"optimum_version": "1.15.0",
|
||||
"quantization": {},
|
||||
"transformers_version": "4.36.2",
|
||||
"use_external_data_format": false
|
||||
}
|
||||
|
|
@ -0,0 +1,51 @@
|
|||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"cls_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"mask_token": {
|
||||
"content": "<mask>",
|
||||
"lstrip": true,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<pad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"sep_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
BIN
resources/models/paraphrase-multilingual-MiniLM-L12-v2-onnx-Q/tokenizer.json
(Stored with Git LFS)
Normal file
BIN
resources/models/paraphrase-multilingual-MiniLM-L12-v2-onnx-Q/tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
|
|
@ -0,0 +1,64 @@
|
|||
{
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<pad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"3": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"250001": {
|
||||
"content": "<mask>",
|
||||
"lstrip": true,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"cls_token": "<s>",
|
||||
"do_lower_case": true,
|
||||
"eos_token": "</s>",
|
||||
"mask_token": "<mask>",
|
||||
"max_length": 128,
|
||||
"model_max_length": 512,
|
||||
"pad_to_multiple_of": null,
|
||||
"pad_token": "<pad>",
|
||||
"pad_token_type_id": 0,
|
||||
"padding_side": "right",
|
||||
"sep_token": "</s>",
|
||||
"stride": 0,
|
||||
"strip_accents": null,
|
||||
"tokenize_chinese_chars": true,
|
||||
"tokenizer_class": "BertTokenizer",
|
||||
"truncation_side": "right",
|
||||
"truncation_strategy": "longest_first",
|
||||
"unk_token": "<unk>"
|
||||
}
|
||||
BIN
resources/models/paraphrase-multilingual-MiniLM-L12-v2-onnx-Q/unigram.json
(Stored with Git LFS)
Normal file
BIN
resources/models/paraphrase-multilingual-MiniLM-L12-v2-onnx-Q/unigram.json
(Stored with Git LFS)
Normal file
Binary file not shown.
Loading…
Add table
Add a link
Reference in a new issue