Data and filtering models of our financial open-source YiZhao Dataset.
AI & ML interests
None defined yet.
Recent Activity
View all activity
Organization Card
Text Machine Group (TMG) from Harbin Institute of Technology (Shenzhen). 🔥
Collections
3
-
KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model
Paper • 2501.01028 • Published • 15 -
HIT-TMG/KaLM-embedding-multilingual-mini-v1
Sentence Similarity • Updated • 2.14k • 25 -
HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1
Sentence Similarity • Updated • 4.86k • 32 -
HIT-TMG/KaLM-embedding-multilingual-max-instruct-v1.5
Updated • 9
Data and filtering models of our financial open-source YiZhao Dataset.
-
KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model
Paper • 2501.01028 • Published • 15 -
HIT-TMG/KaLM-embedding-multilingual-mini-v1
Sentence Similarity • Updated • 2.14k • 25 -
HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1
Sentence Similarity • Updated • 4.86k • 32 -
HIT-TMG/KaLM-embedding-multilingual-max-instruct-v1.5
Updated • 9
models
19

HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v2
Updated
•
13

HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1-GGUF
Sentence Similarity
•
Updated
•
36

HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1.5-GGUF
Sentence Similarity
•
Updated
•
120

HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1.5
Sentence Similarity
•
Updated
•
74k
•
•
59

HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1
Sentence Similarity
•
Updated
•
4.86k
•
32

HIT-TMG/KaLM-embedding-multilingual-mini-unsupervised
Updated
•
15

HIT-TMG/bge-m3_RAG-conversational-IR
Sentence Similarity
•
Updated
•
26
•
1

HIT-TMG/KaLM-embedding-multilingual-max-instruct-v1.5
Updated
•
9

HIT-TMG/KaLM-embedding-multilingual-mini-v1
Sentence Similarity
•
Updated
•
2.14k
•
25

HIT-TMG/Mixtral_13B_Chat_RAG-Reader
Text Generation
•
Updated
•
13
datasets
5
HIT-TMG/YiZhao
Viewer
•
Updated
•
47.5M
•
293
•
6
HIT-TMG/KaLM-embedding-pretrain-data
Viewer
•
Updated
•
23.7M
•
1.06k
•
3
HIT-TMG/MultiSkill
Viewer
•
Updated
•
1k
•
41
HIT-TMG/TruthReader_RAG_train
Viewer
•
Updated
•
7.16k
•
62
•
5
HIT-TMG/Hansel
Viewer
•
Updated
•
7.81M
•
1.37k
•
8