yaniseuranova
commited on
Commit
•
2765549
1
Parent(s):
b80fb90
Add SetFit model
Browse files- 1_Pooling/config.json +3 -3
- README.md +152 -74
- config.json +14 -10
- config_sentence_transformers.json +3 -3
- model.safetensors +2 -2
- model_head.pkl +2 -2
- sentence_bert_config.json +1 -1
- special_tokens_map.json +1 -1
- tokenizer.json +2 -2
- tokenizer_config.json +6 -16
1_Pooling/config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"word_embedding_dimension":
|
3 |
-
"pooling_mode_cls_token":
|
4 |
-
"pooling_mode_mean_tokens":
|
5 |
"pooling_mode_max_tokens": false,
|
6 |
"pooling_mode_mean_sqrt_len_tokens": false,
|
7 |
"pooling_mode_weightedmean_tokens": false,
|
|
|
1 |
{
|
2 |
+
"word_embedding_dimension": 1024,
|
3 |
+
"pooling_mode_cls_token": true,
|
4 |
+
"pooling_mode_mean_tokens": false,
|
5 |
"pooling_mode_max_tokens": false,
|
6 |
"pooling_mode_mean_sqrt_len_tokens": false,
|
7 |
"pooling_mode_weightedmean_tokens": false,
|
README.md
CHANGED
@@ -1,31 +1,26 @@
|
|
1 |
---
|
|
|
2 |
library_name: setfit
|
|
|
|
|
|
|
3 |
tags:
|
4 |
- setfit
|
5 |
- sentence-transformers
|
6 |
- text-classification
|
7 |
- generated_from_setfit_trainer
|
8 |
-
base_model: sentence-transformers/all-mpnet-base-v2
|
9 |
widget:
|
10 |
-
- text:
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
and
|
16 |
-
- text:
|
17 |
-
|
18 |
-
Internet Protocol Stack, as defined by ICANN?
|
19 |
-
- text: >-
|
20 |
-
What distinguishes a transforming industry from one that merely innovates to
|
21 |
-
existing practices?
|
22 |
-
- text: >-
|
23 |
-
How can artificial intelligence systems balance individual autonomy with
|
24 |
-
collective responsibility in decision-making processes?
|
25 |
-
pipeline_tag: text-classification
|
26 |
inference: true
|
27 |
model-index:
|
28 |
-
- name: SetFit
|
29 |
results:
|
30 |
- task:
|
31 |
type: text-classification
|
@@ -36,21 +31,13 @@ model-index:
|
|
36 |
split: test
|
37 |
metrics:
|
38 |
- type: accuracy
|
39 |
-
value:
|
40 |
name: Accuracy
|
41 |
-
language:
|
42 |
-
- en
|
43 |
---
|
44 |
|
45 |
-
#
|
46 |
-
|
47 |
-
The goal of this model is to classify users queries in a RAG pipeline between two classes 'semantic' and 'lexical'. This allow an easy query routing in the context of hybrid search
|
48 |
-
and alpha tuning for hybrid search. A query is considered 'semantic' if it doesn't contain any particular jargon, proper noun, technical terms, ect.. on the other hand it is considered lexical
|
49 |
-
if there are precise keywords than can be used to make a lexical search (BM25 for example).
|
50 |
-
|
51 |
-
The model is very small and fast, thus enabling a very cost-effective approach for query routing comparing to use large LLMs such as GPT4 for query routing !
|
52 |
|
53 |
-
|
54 |
|
55 |
The model has been trained using an efficient few-shot learning technique that involves:
|
56 |
|
@@ -61,9 +48,9 @@ The model has been trained using an efficient few-shot learning technique that i
|
|
61 |
|
62 |
### Model Description
|
63 |
- **Model Type:** SetFit
|
64 |
-
- **Sentence Transformer body:** [
|
65 |
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
|
66 |
-
- **Maximum Sequence Length:**
|
67 |
- **Number of Classes:** 2 classes
|
68 |
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
|
69 |
<!-- - **Language:** Unknown -->
|
@@ -76,17 +63,17 @@ The model has been trained using an efficient few-shot learning technique that i
|
|
76 |
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
77 |
|
78 |
### Model Labels
|
79 |
-
| Label | Examples
|
80 |
-
|
81 |
-
| lexical | <ul><li>
|
82 |
-
| semantic | <ul><li>
|
83 |
|
84 |
## Evaluation
|
85 |
|
86 |
### Metrics
|
87 |
| Label | Accuracy |
|
88 |
|:--------|:---------|
|
89 |
-
| **all** |
|
90 |
|
91 |
## Uses
|
92 |
|
@@ -104,9 +91,9 @@ Then you can load this model and run inference.
|
|
104 |
from setfit import SetFitModel
|
105 |
|
106 |
# Download from the 🤗 Hub
|
107 |
-
model = SetFitModel.from_pretrained("yaniseuranova/setfit-
|
108 |
# Run inference
|
109 |
-
preds = model("What
|
110 |
```
|
111 |
|
112 |
<!--
|
@@ -138,12 +125,12 @@ preds = model("What distinguishes a transforming industry from one that merely i
|
|
138 |
### Training Set Metrics
|
139 |
| Training set | Min | Median | Max |
|
140 |
|:-------------|:----|:--------|:----|
|
141 |
-
| Word count | 4 |
|
142 |
|
143 |
| Label | Training Sample Count |
|
144 |
|:---------|:----------------------|
|
145 |
-
| lexical |
|
146 |
-
| semantic |
|
147 |
|
148 |
### Training Hyperparameters
|
149 |
- batch_size: (8, 8)
|
@@ -165,39 +152,130 @@ preds = model("What distinguishes a transforming industry from one that merely i
|
|
165 |
### Training Results
|
166 |
| Epoch | Step | Training Loss | Validation Loss |
|
167 |
|:-------:|:--------:|:-------------:|:---------------:|
|
168 |
-
| 0.
|
169 |
-
| 0.
|
170 |
-
| 0.
|
171 |
-
| 0.
|
172 |
-
| 0.
|
173 |
-
| 0.
|
174 |
-
| 0.
|
175 |
-
| 0.
|
176 |
-
| 0.
|
177 |
-
| 0.
|
178 |
-
|
|
179 |
-
|
|
180 |
-
|
|
181 |
-
|
|
182 |
-
|
|
183 |
-
|
|
184 |
-
|
|
185 |
-
|
|
186 |
-
|
|
187 |
-
|
|
188 |
-
|
|
189 |
-
|
|
190 |
-
|
|
191 |
-
|
|
192 |
-
|
|
193 |
-
|
|
194 |
-
|
|
195 |
-
|
|
196 |
-
|
|
197 |
-
|
|
198 |
-
|
|
199 |
-
|
|
200 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
201 |
|
202 |
* The bold row denotes the saved checkpoint.
|
203 |
### Framework Versions
|
|
|
1 |
---
|
2 |
+
base_model: BAAI/bge-m3
|
3 |
library_name: setfit
|
4 |
+
metrics:
|
5 |
+
- accuracy
|
6 |
+
pipeline_tag: text-classification
|
7 |
tags:
|
8 |
- setfit
|
9 |
- sentence-transformers
|
10 |
- text-classification
|
11 |
- generated_from_setfit_trainer
|
|
|
12 |
widget:
|
13 |
+
- text: How does technology impact our daily lives and what benefits can it bring
|
14 |
+
to various activities?
|
15 |
+
- text: How do organizations effectively deploy and manage machine learning algorithms
|
16 |
+
to drive business value?
|
17 |
+
- text: What are the key considerations for organizing and managing computer lab resources
|
18 |
+
and tracking their status?
|
19 |
+
- text: How can batch processing improve the efficiency of data lake operations?
|
20 |
+
- text: What is the purpose of setting up a CUPS on a server?
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
inference: true
|
22 |
model-index:
|
23 |
+
- name: SetFit with BAAI/bge-m3
|
24 |
results:
|
25 |
- task:
|
26 |
type: text-classification
|
|
|
31 |
split: test
|
32 |
metrics:
|
33 |
- type: accuracy
|
34 |
+
value: 0.8947368421052632
|
35 |
name: Accuracy
|
|
|
|
|
36 |
---
|
37 |
|
38 |
+
# SetFit with BAAI/bge-m3
|
|
|
|
|
|
|
|
|
|
|
|
|
39 |
|
40 |
+
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
|
41 |
|
42 |
The model has been trained using an efficient few-shot learning technique that involves:
|
43 |
|
|
|
48 |
|
49 |
### Model Description
|
50 |
- **Model Type:** SetFit
|
51 |
+
- **Sentence Transformer body:** [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3)
|
52 |
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
|
53 |
+
- **Maximum Sequence Length:** 8192 tokens
|
54 |
- **Number of Classes:** 2 classes
|
55 |
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
|
56 |
<!-- - **Language:** Unknown -->
|
|
|
63 |
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
64 |
|
65 |
### Model Labels
|
66 |
+
| Label | Examples |
|
67 |
+
|:---------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
68 |
+
| lexical | <ul><li>"How does Happeo's search AI work to provide answers to user queries?"</li><li>'What are the primary areas of focus in the domain of Data Science and Analysis?'</li><li>'How can one organize a running event in Belgium?'</li></ul> |
|
69 |
+
| semantic | <ul><li>'What changes can be made to a channel header?'</li><li>'How can hardware capabilities impact the accuracy of motion and object detections?'</li><li>'Who is responsible for managing guarantees and prolongations?'</li></ul> |
|
70 |
|
71 |
## Evaluation
|
72 |
|
73 |
### Metrics
|
74 |
| Label | Accuracy |
|
75 |
|:--------|:---------|
|
76 |
+
| **all** | 0.8947 |
|
77 |
|
78 |
## Uses
|
79 |
|
|
|
91 |
from setfit import SetFitModel
|
92 |
|
93 |
# Download from the 🤗 Hub
|
94 |
+
model = SetFitModel.from_pretrained("yaniseuranova/setfit-rag-hybrid-search-query-router")
|
95 |
# Run inference
|
96 |
+
preds = model("What is the purpose of setting up a CUPS on a server?")
|
97 |
```
|
98 |
|
99 |
<!--
|
|
|
125 |
### Training Set Metrics
|
126 |
| Training set | Min | Median | Max |
|
127 |
|:-------------|:----|:--------|:----|
|
128 |
+
| Word count | 4 | 13.7407 | 28 |
|
129 |
|
130 |
| Label | Training Sample Count |
|
131 |
|:---------|:----------------------|
|
132 |
+
| lexical | 44 |
|
133 |
+
| semantic | 118 |
|
134 |
|
135 |
### Training Hyperparameters
|
136 |
- batch_size: (8, 8)
|
|
|
152 |
### Training Results
|
153 |
| Epoch | Step | Training Loss | Validation Loss |
|
154 |
|:-------:|:--------:|:-------------:|:---------------:|
|
155 |
+
| 0.0005 | 1 | 0.257 | - |
|
156 |
+
| 0.0250 | 50 | 0.1944 | - |
|
157 |
+
| 0.0499 | 100 | 0.2383 | - |
|
158 |
+
| 0.0749 | 150 | 0.1279 | - |
|
159 |
+
| 0.0999 | 200 | 0.0033 | - |
|
160 |
+
| 0.1248 | 250 | 0.0021 | - |
|
161 |
+
| 0.1498 | 300 | 0.0012 | - |
|
162 |
+
| 0.1747 | 350 | 0.0008 | - |
|
163 |
+
| 0.1997 | 400 | 0.0004 | - |
|
164 |
+
| 0.2247 | 450 | 0.0006 | - |
|
165 |
+
| 0.2496 | 500 | 0.0005 | - |
|
166 |
+
| 0.2746 | 550 | 0.0003 | - |
|
167 |
+
| 0.2996 | 600 | 0.0003 | - |
|
168 |
+
| 0.3245 | 650 | 0.0003 | - |
|
169 |
+
| 0.3495 | 700 | 0.0004 | - |
|
170 |
+
| 0.3744 | 750 | 0.0005 | - |
|
171 |
+
| 0.3994 | 800 | 0.0003 | - |
|
172 |
+
| 0.4244 | 850 | 0.0002 | - |
|
173 |
+
| 0.4493 | 900 | 0.0002 | - |
|
174 |
+
| 0.4743 | 950 | 0.0002 | - |
|
175 |
+
| 0.4993 | 1000 | 0.0001 | - |
|
176 |
+
| 0.5242 | 1050 | 0.0001 | - |
|
177 |
+
| 0.5492 | 1100 | 0.0001 | - |
|
178 |
+
| 0.5741 | 1150 | 0.0002 | - |
|
179 |
+
| 0.5991 | 1200 | 0.0001 | - |
|
180 |
+
| 0.6241 | 1250 | 0.0003 | - |
|
181 |
+
| 0.6490 | 1300 | 0.0002 | - |
|
182 |
+
| 0.6740 | 1350 | 0.0001 | - |
|
183 |
+
| 0.6990 | 1400 | 0.0003 | - |
|
184 |
+
| 0.7239 | 1450 | 0.0001 | - |
|
185 |
+
| 0.7489 | 1500 | 0.0002 | - |
|
186 |
+
| 0.7738 | 1550 | 0.0001 | - |
|
187 |
+
| 0.7988 | 1600 | 0.0002 | - |
|
188 |
+
| 0.8238 | 1650 | 0.0002 | - |
|
189 |
+
| 0.8487 | 1700 | 0.0002 | - |
|
190 |
+
| 0.8737 | 1750 | 0.0002 | - |
|
191 |
+
| 0.8987 | 1800 | 0.0003 | - |
|
192 |
+
| 0.9236 | 1850 | 0.0001 | - |
|
193 |
+
| 0.9486 | 1900 | 0.0001 | - |
|
194 |
+
| 0.9735 | 1950 | 0.0001 | - |
|
195 |
+
| 0.9985 | 2000 | 0.0001 | - |
|
196 |
+
| **1.0** | **2003** | **-** | **0.1735** |
|
197 |
+
| 1.0235 | 2050 | 0.0001 | - |
|
198 |
+
| 1.0484 | 2100 | 0.0001 | - |
|
199 |
+
| 1.0734 | 2150 | 0.0001 | - |
|
200 |
+
| 1.0984 | 2200 | 0.0 | - |
|
201 |
+
| 1.1233 | 2250 | 0.0001 | - |
|
202 |
+
| 1.1483 | 2300 | 0.0001 | - |
|
203 |
+
| 1.1732 | 2350 | 0.0001 | - |
|
204 |
+
| 1.1982 | 2400 | 0.0002 | - |
|
205 |
+
| 1.2232 | 2450 | 0.0001 | - |
|
206 |
+
| 1.2481 | 2500 | 0.0 | - |
|
207 |
+
| 1.2731 | 2550 | 0.0001 | - |
|
208 |
+
| 1.2981 | 2600 | 0.0001 | - |
|
209 |
+
| 1.3230 | 2650 | 0.0 | - |
|
210 |
+
| 1.3480 | 2700 | 0.0001 | - |
|
211 |
+
| 1.3729 | 2750 | 0.0001 | - |
|
212 |
+
| 1.3979 | 2800 | 0.0001 | - |
|
213 |
+
| 1.4229 | 2850 | 0.0 | - |
|
214 |
+
| 1.4478 | 2900 | 0.0001 | - |
|
215 |
+
| 1.4728 | 2950 | 0.0001 | - |
|
216 |
+
| 1.4978 | 3000 | 0.0001 | - |
|
217 |
+
| 1.5227 | 3050 | 0.0001 | - |
|
218 |
+
| 1.5477 | 3100 | 0.0 | - |
|
219 |
+
| 1.5726 | 3150 | 0.0 | - |
|
220 |
+
| 1.5976 | 3200 | 0.0001 | - |
|
221 |
+
| 1.6226 | 3250 | 0.0001 | - |
|
222 |
+
| 1.6475 | 3300 | 0.0001 | - |
|
223 |
+
| 1.6725 | 3350 | 0.0001 | - |
|
224 |
+
| 1.6975 | 3400 | 0.0001 | - |
|
225 |
+
| 1.7224 | 3450 | 0.0 | - |
|
226 |
+
| 1.7474 | 3500 | 0.0002 | - |
|
227 |
+
| 1.7723 | 3550 | 0.0001 | - |
|
228 |
+
| 1.7973 | 3600 | 0.0 | - |
|
229 |
+
| 1.8223 | 3650 | 0.0 | - |
|
230 |
+
| 1.8472 | 3700 | 0.0001 | - |
|
231 |
+
| 1.8722 | 3750 | 0.0 | - |
|
232 |
+
| 1.8972 | 3800 | 0.0001 | - |
|
233 |
+
| 1.9221 | 3850 | 0.0 | - |
|
234 |
+
| 1.9471 | 3900 | 0.0 | - |
|
235 |
+
| 1.9720 | 3950 | 0.0001 | - |
|
236 |
+
| 1.9970 | 4000 | 0.0 | - |
|
237 |
+
| 2.0 | 4006 | - | 0.2593 |
|
238 |
+
| 2.0220 | 4050 | 0.0001 | - |
|
239 |
+
| 2.0469 | 4100 | 0.0001 | - |
|
240 |
+
| 2.0719 | 4150 | 0.0 | - |
|
241 |
+
| 2.0969 | 4200 | 0.0001 | - |
|
242 |
+
| 2.1218 | 4250 | 0.0 | - |
|
243 |
+
| 2.1468 | 4300 | 0.0001 | - |
|
244 |
+
| 2.1717 | 4350 | 0.0001 | - |
|
245 |
+
| 2.1967 | 4400 | 0.0001 | - |
|
246 |
+
| 2.2217 | 4450 | 0.0001 | - |
|
247 |
+
| 2.2466 | 4500 | 0.0001 | - |
|
248 |
+
| 2.2716 | 4550 | 0.0 | - |
|
249 |
+
| 2.2966 | 4600 | 0.0 | - |
|
250 |
+
| 2.3215 | 4650 | 0.0 | - |
|
251 |
+
| 2.3465 | 4700 | 0.0001 | - |
|
252 |
+
| 2.3714 | 4750 | 0.0001 | - |
|
253 |
+
| 2.3964 | 4800 | 0.0002 | - |
|
254 |
+
| 2.4214 | 4850 | 0.0001 | - |
|
255 |
+
| 2.4463 | 4900 | 0.0001 | - |
|
256 |
+
| 2.4713 | 4950 | 0.0 | - |
|
257 |
+
| 2.4963 | 5000 | 0.0001 | - |
|
258 |
+
| 2.5212 | 5050 | 0.0001 | - |
|
259 |
+
| 2.5462 | 5100 | 0.0 | - |
|
260 |
+
| 2.5711 | 5150 | 0.0001 | - |
|
261 |
+
| 2.5961 | 5200 | 0.0 | - |
|
262 |
+
| 2.6211 | 5250 | 0.0 | - |
|
263 |
+
| 2.6460 | 5300 | 0.0 | - |
|
264 |
+
| 2.6710 | 5350 | 0.0 | - |
|
265 |
+
| 2.6960 | 5400 | 0.0 | - |
|
266 |
+
| 2.7209 | 5450 | 0.0 | - |
|
267 |
+
| 2.7459 | 5500 | 0.0 | - |
|
268 |
+
| 2.7708 | 5550 | 0.0 | - |
|
269 |
+
| 2.7958 | 5600 | 0.0001 | - |
|
270 |
+
| 2.8208 | 5650 | 0.0 | - |
|
271 |
+
| 2.8457 | 5700 | 0.0 | - |
|
272 |
+
| 2.8707 | 5750 | 0.0 | - |
|
273 |
+
| 2.8957 | 5800 | 0.0 | - |
|
274 |
+
| 2.9206 | 5850 | 0.0 | - |
|
275 |
+
| 2.9456 | 5900 | 0.0001 | - |
|
276 |
+
| 2.9705 | 5950 | 0.0 | - |
|
277 |
+
| 2.9955 | 6000 | 0.0 | - |
|
278 |
+
| 3.0 | 6009 | - | 0.2738 |
|
279 |
|
280 |
* The bold row denotes the saved checkpoint.
|
281 |
### Framework Versions
|
config.json
CHANGED
@@ -1,24 +1,28 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "checkpoints/
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"bos_token_id": 0,
|
|
|
8 |
"eos_token_id": 2,
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
-
"hidden_size":
|
12 |
"initializer_range": 0.02,
|
13 |
-
"intermediate_size":
|
14 |
"layer_norm_eps": 1e-05,
|
15 |
-
"max_position_embeddings":
|
16 |
-
"model_type": "
|
17 |
-
"num_attention_heads":
|
18 |
-
"num_hidden_layers":
|
|
|
19 |
"pad_token_id": 1,
|
20 |
-
"
|
21 |
"torch_dtype": "float32",
|
22 |
"transformers_version": "4.39.0",
|
23 |
-
"
|
|
|
|
|
24 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "checkpoints/step_2003",
|
3 |
"architectures": [
|
4 |
+
"XLMRobertaModel"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
"eos_token_id": 2,
|
10 |
"hidden_act": "gelu",
|
11 |
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 1024,
|
13 |
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 4096,
|
15 |
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 8194,
|
17 |
+
"model_type": "xlm-roberta",
|
18 |
+
"num_attention_heads": 16,
|
19 |
+
"num_hidden_layers": 24,
|
20 |
+
"output_past": true,
|
21 |
"pad_token_id": 1,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
"torch_dtype": "float32",
|
24 |
"transformers_version": "4.39.0",
|
25 |
+
"type_vocab_size": 1,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 250002
|
28 |
}
|
config_sentence_transformers.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"__version__": {
|
3 |
-
"sentence_transformers": "2.
|
4 |
-
"transformers": "4.
|
5 |
-
"pytorch": "1.
|
6 |
},
|
7 |
"prompts": {},
|
8 |
"default_prompt_name": null
|
|
|
1 |
{
|
2 |
"__version__": {
|
3 |
+
"sentence_transformers": "2.2.2",
|
4 |
+
"transformers": "4.33.0",
|
5 |
+
"pytorch": "2.1.2+cu121"
|
6 |
},
|
7 |
"prompts": {},
|
8 |
"default_prompt_name": null
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c53fbde2e0a8e51b9e5ba603737ededaa63700e00099ac3a1c04747711b4d59
|
3 |
+
size 2271064456
|
model_head.pkl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ca465fc25015364d0a19db7bd6ca20b2f8dfd3fa876e23b415f2fcd1959f980
|
3 |
+
size 9087
|
sentence_bert_config.json
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
{
|
2 |
-
"max_seq_length":
|
3 |
"do_lower_case": false
|
4 |
}
|
|
|
1 |
{
|
2 |
+
"max_seq_length": 8192,
|
3 |
"do_lower_case": false
|
4 |
}
|
special_tokens_map.json
CHANGED
@@ -42,7 +42,7 @@
|
|
42 |
"single_word": false
|
43 |
},
|
44 |
"unk_token": {
|
45 |
-
"content": "
|
46 |
"lstrip": false,
|
47 |
"normalized": false,
|
48 |
"rstrip": false,
|
|
|
42 |
"single_word": false
|
43 |
},
|
44 |
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
"lstrip": false,
|
47 |
"normalized": false,
|
48 |
"rstrip": false,
|
tokenizer.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1af481bd08ed9347cf9d3d07c24e5de75a10983819de076436400609e6705686
|
3 |
+
size 17083075
|
tokenizer_config.json
CHANGED
@@ -27,20 +27,12 @@
|
|
27 |
"3": {
|
28 |
"content": "<unk>",
|
29 |
"lstrip": false,
|
30 |
-
"normalized": true,
|
31 |
-
"rstrip": false,
|
32 |
-
"single_word": false,
|
33 |
-
"special": true
|
34 |
-
},
|
35 |
-
"104": {
|
36 |
-
"content": "[UNK]",
|
37 |
-
"lstrip": false,
|
38 |
"normalized": false,
|
39 |
"rstrip": false,
|
40 |
"single_word": false,
|
41 |
"special": true
|
42 |
},
|
43 |
-
"
|
44 |
"content": "<mask>",
|
45 |
"lstrip": true,
|
46 |
"normalized": false,
|
@@ -52,21 +44,19 @@
|
|
52 |
"bos_token": "<s>",
|
53 |
"clean_up_tokenization_spaces": true,
|
54 |
"cls_token": "<s>",
|
55 |
-
"do_lower_case": true,
|
56 |
"eos_token": "</s>",
|
57 |
"mask_token": "<mask>",
|
58 |
-
"max_length":
|
59 |
-
"model_max_length":
|
60 |
"pad_to_multiple_of": null,
|
61 |
"pad_token": "<pad>",
|
62 |
"pad_token_type_id": 0,
|
63 |
"padding_side": "right",
|
64 |
"sep_token": "</s>",
|
|
|
65 |
"stride": 0,
|
66 |
-
"
|
67 |
-
"tokenize_chinese_chars": true,
|
68 |
-
"tokenizer_class": "MPNetTokenizer",
|
69 |
"truncation_side": "right",
|
70 |
"truncation_strategy": "longest_first",
|
71 |
-
"unk_token": "
|
72 |
}
|
|
|
27 |
"3": {
|
28 |
"content": "<unk>",
|
29 |
"lstrip": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
30 |
"normalized": false,
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
+
"250001": {
|
36 |
"content": "<mask>",
|
37 |
"lstrip": true,
|
38 |
"normalized": false,
|
|
|
44 |
"bos_token": "<s>",
|
45 |
"clean_up_tokenization_spaces": true,
|
46 |
"cls_token": "<s>",
|
|
|
47 |
"eos_token": "</s>",
|
48 |
"mask_token": "<mask>",
|
49 |
+
"max_length": 8192,
|
50 |
+
"model_max_length": 8192,
|
51 |
"pad_to_multiple_of": null,
|
52 |
"pad_token": "<pad>",
|
53 |
"pad_token_type_id": 0,
|
54 |
"padding_side": "right",
|
55 |
"sep_token": "</s>",
|
56 |
+
"sp_model_kwargs": {},
|
57 |
"stride": 0,
|
58 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
|
|
|
|
59 |
"truncation_side": "right",
|
60 |
"truncation_strategy": "longest_first",
|
61 |
+
"unk_token": "<unk>"
|
62 |
}
|