Sentence Similarity
Transformers
Safetensors
Ganda
sagepond_un_model
feature-extraction
luganda
embeddings
sentence-embeddings
semantic-search
research
custom_code
Eval Results (legacy)
Instructions to use sagepond/embedding-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sagepond/embedding-small with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("sagepond/embedding-small", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from sagepond/embedding-small: direct link, hf CLI and curl.
- Browser
- Download file 1.03 kB
-
https://huggingface.co/sagepond/embedding-small/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://sagepond/embedding-small/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/sagepond/embedding-small/resolve/main/tokenizer_config.json
1.03 kB
| { | |
| "added_tokens_decoder": { | |
| "0": { | |
| "content": "<pad>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "1": { | |
| "content": "<unk>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "2": { | |
| "content": "<s>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "3": { | |
| "content": "</s>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "auto_map": { | |
| "AutoTokenizer": [ | |
| "ganda_tokenizer.UnModelTokenizer", | |
| null | |
| ] | |
| }, | |
| "backend": "custom", | |
| "bos_token": "<s>", | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "</s>", | |
| "model_max_length": 600, | |
| "pad_token": "<pad>", | |
| "tokenizer_class": "UnModelTokenizer", | |
| "unk_token": "<unk>" | |
| } | |