Hugging Face's logo

pkshatech
/
GLuCoSE-base-ja

Sentence Similarity
sentence-transformers
PyTorch
Transformers
Japanese
luke
feature-extraction
Model card Files Community
1
akiFQC commited on
Commit
625ec27
•
1 Parent(s): 175a388

update: weight and readme

Browse files
Files changed (3) hide show
  1. README.md +2 -2
  2. README_JA.md +3 -3
  3. pytorch_model.bin +1 -1
README.md CHANGED
@@ -85,7 +85,7 @@ Evaluation by Spearman's correlation coefficient and Pearson's correlation coeff
85
  | --- | --- | --- |
86
  | [text-embedding-ada-002](https://platform.openai.com/docs/guides/embeddings) |0.837[^2] | 0.790[^2] |
87
  | [pkshatech/simcse-ja-bert-base-clcmlp](https://huggingface.co/pkshatech/simcse-ja-bert-base-clcmlp)[^3] | 0.850 | 0.801 |
88
- | pkshatech/GLuCoSE-base-ja | **0.865** | **0.821** |
89
 
90
  ### Zero-shot Search ([AIO3](https://sites.google.com/view/project-aio/competition3?authuser=0) dev set)
91
  Evaluation by top-k retrieval accuracy[^4] (the fraction of questions that have a correct answer in the top-k retrieved documents at least once.)
@@ -93,7 +93,7 @@ Evaluation by top-k retrieval accuracy[^4] (the fraction of questions that have
93
  | --- | --- | --- | --- | --- |
94
  | [text-embedding-ada-002](https://platform.openai.com/docs/guides/embeddings) | 33.50 | **57.80** | 65.10 | 76.60 |
95
  | [pkshatech/simcse-ja-bert-base-clcmlp](https://huggingface.co/pkshatech/simcse-ja-bert-base-clcmlp)[^3] | 30.60 | 54.50 | 62.50 | 76.70 |
96
- | pkshatech/GLuCoSE-base-ja | **34.20** | 57.50 | **65.20** | **77.60** |
97
 
98
 
99
  # Authors
 
85
  | --- | --- | --- |
86
  | [text-embedding-ada-002](https://platform.openai.com/docs/guides/embeddings) |0.837[^2] | 0.790[^2] |
87
  | [pkshatech/simcse-ja-bert-base-clcmlp](https://huggingface.co/pkshatech/simcse-ja-bert-base-clcmlp)[^3] | 0.850 | 0.801 |
88
+ | pkshatech/GLuCoSE-base-ja | **0.864** | **0.818** |
89
 
90
  ### Zero-shot Search ([AIO3](https://sites.google.com/view/project-aio/competition3?authuser=0) dev set)
91
  Evaluation by top-k retrieval accuracy[^4] (the fraction of questions that have a correct answer in the top-k retrieved documents at least once.)
 
93
  | --- | --- | --- | --- | --- |
94
  | [text-embedding-ada-002](https://platform.openai.com/docs/guides/embeddings) | 33.50 | **57.80** | 65.10 | 76.60 |
95
  | [pkshatech/simcse-ja-bert-base-clcmlp](https://huggingface.co/pkshatech/simcse-ja-bert-base-clcmlp)[^3] | 30.60 | 54.50 | 62.50 | 76.70 |
96
+ | pkshatech/GLuCoSE-base-ja | **36.10** | **59.40** | **66.40** | **78.30** |
97
 
98
 
99
  # Authors
README_JA.md CHANGED
@@ -85,15 +85,15 @@ Spearmanの相関係数、Pearsonの相関係数で評価
85
  | --- | --- | --- |
86
  | [text-embedding-ada-002](https://platform.openai.com/docs/guides/embeddings) | 0.837[^2] | 0.790[^2] |
87
  | [pkshatech/simcse-ja-bert-base-clcmlp](https://huggingface.co/pkshatech/simcse-ja-bert-base-clcmlp)[^3]　| 0.850 | 0.801 |
88
- | pkshatech/GLuCoSE-base-ja | **0.865** | **0.821** |
89
 
90
  ### zero-shot 検索([第3回AI王](https://sites.google.com/view/project-aio/competition3?authuser=0) dev set)
91
  top-k　retrieval accuracy[^4] (検索された上位k個の文書に少なくとも1回は正解が含まれる問題の割合)で評価
92
  | モデル | Top-1 | Top-5| Top-10| Top-50|
93
  | --- | --- | --- |---|---|
94
- | [text-embedding-ada-002](https://platform.openai.com/docs/guides/embeddings) |33.50 | **57.80** | 65.10| 76.60|
95
  | [pkshatech/simcse-ja-bert-base-clcmlp](https://huggingface.co/pkshatech/simcse-ja-bert-base-clcmlp)[^3]　| 30.60 | 54.50 | 62.50 | 76.70 |
96
- | pkshatech/GLuCoSE-base-ja | **34.20** | 57.50 | **65.20** | **77.60** |
97
 
98
  # Authors
99
  [Akihiko Fukuchi](https://huggingface.co/akiFQC), [Yuichiroh Hoshino](https://huggingface.co/Yuichiroh), [Yotarow Watanabe](https://huggingface.co/yotarow)
 
85
  | --- | --- | --- |
86
  | [text-embedding-ada-002](https://platform.openai.com/docs/guides/embeddings) | 0.837[^2] | 0.790[^2] |
87
  | [pkshatech/simcse-ja-bert-base-clcmlp](https://huggingface.co/pkshatech/simcse-ja-bert-base-clcmlp)[^3]　| 0.850 | 0.801 |
88
+ | pkshatech/GLuCoSE-base-ja | **0.864** | **0.818** |
89
 
90
  ### zero-shot 検索([第3回AI王](https://sites.google.com/view/project-aio/competition3?authuser=0) dev set)
91
  top-k　retrieval accuracy[^4] (検索された上位k個の文書に少なくとも1回は正解が含まれる問題の割合)で評価
92
  | モデル | Top-1 | Top-5| Top-10| Top-50|
93
  | --- | --- | --- |---|---|
94
+ | [text-embedding-ada-002](https://platform.openai.com/docs/guides/embeddings) |33.50 | 57.80 | 65.10| 76.60|
95
  | [pkshatech/simcse-ja-bert-base-clcmlp](https://huggingface.co/pkshatech/simcse-ja-bert-base-clcmlp)[^3]　| 30.60 | 54.50 | 62.50 | 76.70 |
96
+ | pkshatech/GLuCoSE-base-ja | **36.10** | **59.40** | **66.40** | **78.30** |
97
 
98
  # Authors
99
  [Akihiko Fukuchi](https://huggingface.co/akiFQC), [Yuichiroh Hoshino](https://huggingface.co/Yuichiroh), [Yotarow Watanabe](https://huggingface.co/yotarow)
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3c698698882f31d4ce74494bcc357c7fe0525c4401907520dd529dffc5b61bc
3
  size 532361569
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d48a302b78a8a81d94ecfde8ee0cd4d316d8e43bee0c25c81fd08455b1fdfcc
3
  size 532361569