Downloads · 30 days
170
10% of all-time downloads
KaLM-embedding-multilingual-mini-instruct-v1-GGUF
HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1-GGUF
KaLM-embedding-multilingual-mini-instruct-v1-GGUF is a sentence similarity model from HIT-TMG. Use it when you need a score for how close two texts are. It is set up for sentence-transformers. The card lists the license as mit.
All-time downloads
1.8K
Public
Repo size
6.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf6.1 GB · 100%
At a glance
- Task
- Sentence Similarity
- Library
- sentence-transformers
- License
- mit
- Access
- Public
- Created
- Mar 11, 2025
- Updated
- Mar 14, 2025
- SHA
- 3002518f
Base models
Model card
From the Hugging Face model README
Using llama.cpp for GGUF conversion.
Original model: HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1
Run them directly with llama.cpp:
./llama-embedding \
--batch-size 512 \
--ctx-size 512 \
-m KaLM-embedding-multilingual-mini-instruct-v1-GGUF/model.f32.gguf \
--pooling mean \
-p "this is a test sentence for llama cpp"
It is important to note that this model uses the mean pooling method, so the --pooling parameter needs to be specified as mean when invoking it.
Our tests on LM Studio have not yet been successful, and it is unclear whether this is related to the default pooling method used by LM Studio.
If any developers are familiar with how to specify the pooling method for embedding models in LM Studio, we welcome you to contact us for further discussion via the email: [email protected]
- Task
- Sentence Similarity
- Library
- sentence-transformers
- License
- mit
- Languages
- zh, en
- Created
- Mar 11, 2025
- Updated
- Mar 14, 2025