iconitech commited on
Commit
88bf055
·
verified ·
1 Parent(s): 52369d2

update model improvements

Browse files
Files changed (2) hide show
  1. README.md +31 -31
  2. model.safetensors +1 -1
README.md CHANGED
@@ -4,35 +4,35 @@ tags:
4
  - sentence-similarity
5
  - feature-extraction
6
  - generated_from_trainer
7
- - dataset_size:40
8
  - loss:TripletLoss
9
  base_model: sentence-transformers/all-mpnet-base-v2
10
  widget:
11
- - source_sentence: howitzer arm quarterback
12
  sentences:
13
- - opens and flips seamlessly to carry verticals while tracking ball
14
- - deep balls die at 45 yards and force WRs to slow up
15
- - flicks his wrist and sends 60-yard lasers in stride downfield
16
- - source_sentence: durability concerns prospect
17
  sentences:
18
- - started every game for four straight seasons without issue
19
- - missed significant time with repeated lower-body injuries
20
- - first step flies off the line and shocks blockers
21
- - source_sentence: throws with effortless velocity
22
  sentences:
23
  - overthrows wide-open seams and turf short hooks
24
- - passes hang in the air and allow DBs to close
25
- - ball jumps off his hand and arrives to tight windows before defenders react
26
- - source_sentence: elite athletic traits
27
- sentences:
28
- - drops hips and absorbs bull rushes without giving ground
29
- - clocked a 4.34 forty and posted a 40″ vertical despite 240-lb frame
30
- - testing numbers show average burst and straight-line speed
31
- - source_sentence: frequent stints on sideline
32
  sentences:
33
  - click-and-close burst plus natural hands yield PBUs
34
- - left five games early due to nagging ankles
35
- - ironman who played 95 % of snaps
 
 
 
 
 
36
  pipeline_tag: sentence-similarity
37
  library_name: sentence-transformers
38
  ---
@@ -87,9 +87,9 @@ from sentence_transformers import SentenceTransformer
87
  model = SentenceTransformer("sentence_transformers_model_id")
88
  # Run inference
89
  sentences = [
90
- 'frequent stints on sideline',
91
- 'left five games early due to nagging ankles',
92
- 'ironman who played 95 % of snaps',
93
  ]
94
  embeddings = model.encode(sentences)
95
  print(embeddings.shape)
@@ -143,19 +143,19 @@ You can finetune this model on your own dataset.
143
 
144
  #### Unnamed Dataset
145
 
146
- * Size: 40 training samples
147
  * Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>sentence_2</code>
148
- * Approximate statistics based on the first 40 samples:
149
  | | sentence_0 | sentence_1 | sentence_2 |
150
  |:--------|:--------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
151
  | type | string | string | string |
152
- | details | <ul><li>min: 5 tokens</li><li>mean: 6.53 tokens</li><li>max: 9 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 12.88 tokens</li><li>max: 20 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 11.22 tokens</li><li>max: 15 tokens</li></ul> |
153
  * Samples:
154
- | sentence_0 | sentence_1 | sentence_2 |
155
- |:--------------------------------------------|:-----------------------------------------------------------------------------------|:------------------------------------------------------------------------|
156
- | <code>explosive lower body</code> | <code>first step flies off the line and shocks blockers</code> | <code>lacks suddenness and is slow out of his stance</code> |
157
- | <code>technically sound route runner</code> | <code>sells stems with subtle head fakes and snaps off breaks at full speed</code> | <code>relies purely on speed and rounds off cuts</code> |
158
- | <code>durability concerns prospect</code> | <code>missed significant time with repeated lower-body injuries</code> | <code>started every game for four straight seasons without issue</code> |
159
  * Loss: [<code>TripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#tripletloss) with these parameters:
160
  ```json
161
  {
 
4
  - sentence-similarity
5
  - feature-extraction
6
  - generated_from_trainer
7
+ - dataset_size:41
8
  - loss:TripletLoss
9
  base_model: sentence-transformers/all-mpnet-base-v2
10
  widget:
11
+ - source_sentence: elite ball production DB
12
  sentences:
13
+ - rarely gets his head around and allows catches in phase
14
+ - times his breaks and plucks interceptions away from receivers
15
+ - sprays throws and forces receivers to adjust behind them
16
+ - source_sentence: vision and patience RB
17
  sentences:
18
+ - hamstring tweaks kept him out of key practices each year
19
+ - gets impatient and bounces, resulting in no gain
20
+ - presses hole, forces defender to commit, then explodes through the gap
21
+ - source_sentence: turn and run fluidity
22
  sentences:
23
  - overthrows wide-open seams and turf short hooks
24
+ - effortlessly flips, locates, and finishes with secure hands
25
+ - tight lower half leads to contact catches
26
+ - source_sentence: excellent run instincts
 
 
 
 
 
27
  sentences:
28
  - click-and-close burst plus natural hands yield PBUs
29
+ - string of efficient decisions keeps offense on schedule
30
+ - hesitates and wastes steps, leading to tackles for loss
31
+ - source_sentence: corner with fluid hips
32
+ sentences:
33
+ - opens and flips seamlessly to carry verticals while tracking ball
34
+ - praised for leadership and A+ character
35
+ - stiff in transition and loses body control at catch point
36
  pipeline_tag: sentence-similarity
37
  library_name: sentence-transformers
38
  ---
 
87
  model = SentenceTransformer("sentence_transformers_model_id")
88
  # Run inference
89
  sentences = [
90
+ 'corner with fluid hips',
91
+ 'opens and flips seamlessly to carry verticals while tracking ball',
92
+ 'stiff in transition and loses body control at catch point',
93
  ]
94
  embeddings = model.encode(sentences)
95
  print(embeddings.shape)
 
143
 
144
  #### Unnamed Dataset
145
 
146
+ * Size: 41 training samples
147
  * Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>sentence_2</code>
148
+ * Approximate statistics based on the first 41 samples:
149
  | | sentence_0 | sentence_1 | sentence_2 |
150
  |:--------|:--------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
151
  | type | string | string | string |
152
+ | details | <ul><li>min: 4 tokens</li><li>mean: 6.46 tokens</li><li>max: 9 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 12.78 tokens</li><li>max: 20 tokens</li></ul> | <ul><li>min: 7 tokens</li><li>mean: 11.17 tokens</li><li>max: 15 tokens</li></ul> |
153
  * Samples:
154
+ | sentence_0 | sentence_1 | sentence_2 |
155
+ |:---------------------------------------------|:-----------------------------------------------------------------------------------------|:-----------------------------------------------------------------|
156
+ | <code>throws with effortless velocity</code> | <code>ball jumps off his hand and arrives to tight windows before defenders react</code> | <code>passes hang in the air and allow DBs to close</code> |
157
+ | <code>persistent soft-tissue injuries</code> | <code>hamstring tweaks kept him out of key practices each year</code> | <code>has never appeared on the injury report</code> |
158
+ | <code>injury prone track record</code> | <code>three different surgeries in college raise red flags</code> | <code>medical checks came back clean with no missed games</code> |
159
  * Loss: [<code>TripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#tripletloss) with these parameters:
160
  ```json
161
  {
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3db329a8cad0f2d41a293445e918b94740a8f8fc159982ccebdd6040468e3ba6
3
  size 437967672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6da5b7c6a7721c7f135e6ee952d0f55b8c403458b120fefa3891716edbaf01c5
3
  size 437967672