Instructions to use C10X/int8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Model2Vec
How to use C10X/int8 with Model2Vec:
from model2vec import StaticModel model = StaticModel.from_pretrained("C10X/int8") - sentence-transformers
How to use C10X/int8 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("C10X/int8") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
Upload config.json with huggingface_hub
Browse files- config.json +13 -0
config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "model2vec",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"StaticModel"
|
| 5 |
+
],
|
| 6 |
+
"tokenizer_name": "Qwen/Qwen3-Reranker-0.6B",
|
| 7 |
+
"apply_pca": 256,
|
| 8 |
+
"apply_zipf": null,
|
| 9 |
+
"sif_coefficient": 0.0001,
|
| 10 |
+
"hidden_dim": 256,
|
| 11 |
+
"seq_length": 1000000,
|
| 12 |
+
"normalize": true
|
| 13 |
+
}
|