Hugging Face's logo

HIT-TMG
/
KaLM-embedding-multilingual-mini-instruct-v1

Sentence Similarity
sentence-transformers
Safetensors
qwen2
feature-extraction
mteb
Eval Results
text-embeddings-inference
Model card Files
xet
Community
4
YanshekWoo commited on
Commit
edf9656
·
verified ·
1 Parent(s): 91f38cf

1022

Browse files
Files changed (1) hide show
  1. README.md +4 -2
README.md CHANGED
@@ -20127,9 +20127,10 @@ KaLM-embedding-multilingual-mini is trained from [Qwen/Qwen2-0.5B](https://huggi
20127
  - [x] Model Checkpoint
20128
  - [x] [KaLM-embedding-multilingual-mini-v1](https://huggingface.co/HIT-TMG/KaLM-embedding-multilingual-mini-v1)
20129
  - [x] [KaLM-embedding-multilingual-mini-instruct-v1](https://huggingface.co/HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1)
 
20130
  - [ ] KaLM-embedding-multilingual-max-v1
20131
  - [x] Training and Evaluation Code: [HITsz-TMG/KaLM-Embedding](https://github.com/HITsz-TMG/KaLM-Embedding)
20132
- - [ ] Technical Report (in 2024)
20133
  - [ ] Training Data
20134
 
20135
 
@@ -20141,7 +20142,8 @@ KaLM-embedding-multilingual-mini is trained from [Qwen/Qwen2-0.5B](https://huggi
20141
  | [bge-m3 (dense)](https://huggingface.co/BAAI/bge-m3) | 560M | 60.80 | 59.84 | 60.32
20142
  | [gte-multilingual-base (dense)](https://huggingface.co/Alibaba-NLP/gte-multilingual-base) | **305M** | 62.72 | 61.40 | 62.06
20143
  | [KaLM-embedding-multilingual-mini-v1](https://huggingface.co/HIT-TMG/KaLM-embedding-multilingual-mini-v1) | 494M | 62.31 | 61.87 | 62.09
20144
- | [KaLM-embedding-multilingual-mini-instruct-v1](https://huggingface.co/HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1) | 494M | **63.57** | **64.74** | **64.16**
 
20145
 
20146
 
20147
 
 
20127
  - [x] Model Checkpoint
20128
  - [x] [KaLM-embedding-multilingual-mini-v1](https://huggingface.co/HIT-TMG/KaLM-embedding-multilingual-mini-v1)
20129
  - [x] [KaLM-embedding-multilingual-mini-instruct-v1](https://huggingface.co/HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1)
20130
+ - [x] [KaLM-embedding-multilingual-mini-instruct-v1.5](https://huggingface.co/HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1.5)
20131
  - [ ] KaLM-embedding-multilingual-max-v1
20132
  - [x] Training and Evaluation Code: [HITsz-TMG/KaLM-Embedding](https://github.com/HITsz-TMG/KaLM-Embedding)
20133
+ - [x] Technical Report: [KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model](https://arxiv.org/abs/2501.01028)
20134
  - [ ] Training Data
20135
 
20136
 
 
20142
  | [bge-m3 (dense)](https://huggingface.co/BAAI/bge-m3) | 560M | 60.80 | 59.84 | 60.32
20143
  | [gte-multilingual-base (dense)](https://huggingface.co/Alibaba-NLP/gte-multilingual-base) | **305M** | 62.72 | 61.40 | 62.06
20144
  | [KaLM-embedding-multilingual-mini-v1](https://huggingface.co/HIT-TMG/KaLM-embedding-multilingual-mini-v1) | 494M | 62.31 | 61.87 | 62.09
20145
+ | [KaLM-embedding-multilingual-mini-instruct-v1](https://huggingface.co/HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1) | 494M | 63.57 | 64.74 | 64.16
20146
+ | [KaLM-embedding-multilingual-mini-instruct-v1.5](https://huggingface.co/HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1.5) | 494M | **64.13** | **64.94** | **64.53**
20147
 
20148
 
20149