Sentence Similarity
Transformers
Safetensors
embedding_gemma2
feature-extraction
embeddinggemma
quantization
post-training-quantization
int4
4-bit precision
text-embeddings
semantic-search
retrieval
low-memory
cpu
8-bit precision
Instructions to use ewin-reg/embeddinggemma-2-0.2B-Quantized-text with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ewin-reg/embeddinggemma-2-0.2B-Quantized-text with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("ewin-reg/embeddinggemma-2-0.2B-Quantized-text") model = AutoModel.from_pretrained("ewin-reg/embeddinggemma-2-0.2B-Quantized-text", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download quant_config.json from ewin-reg/embeddinggemma-2-0.2B-Quantized-text: direct link, hf CLI and curl.
- Browser
- Download file 211 Bytes
-
https://huggingface.co/ewin-reg/embeddinggemma-2-0.2B-Quantized-text/resolve/main/quant_config.json
- Command line
-
hf download hf://ewin-reg/embeddinggemma-2-0.2B-Quantized-text/quant_config.json
-
curl -L -o quant_config.json https://huggingface.co/ewin-reg/embeddinggemma-2-0.2B-Quantized-text/resolve/main/quant_config.json
211 Bytes
| { | |
| "body": [ | |
| 4, | |
| 16 | |
| ], | |
| "table": [ | |
| 4, | |
| 16 | |
| ], | |
| "embed_scale": { | |
| "embed_tokens": 22.627416610717773 | |
| }, | |
| "scheme": "group-wise asymmetric min-max, fp16 scale and min, uint8 bit-packed" | |
| } |