Sentence Similarity
sentence-transformers
Safetensors
bert
embedding
context-curation
long-context
memory-management
retrieval
text-embeddings-inference
Instructions to use SkyIsNotGreen/splinter-encoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use SkyIsNotGreen/splinter-encoder with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("SkyIsNotGreen/splinter-encoder") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Download gate.json from SkyIsNotGreen/splinter-encoder: direct link, hf CLI and curl.
- Browser
- Download file 2.15 kB
-
https://huggingface.co/SkyIsNotGreen/splinter-encoder/resolve/main/gate.json
- Command line
-
hf download hf://SkyIsNotGreen/splinter-encoder/gate.json
-
curl -L -o gate.json https://huggingface.co/SkyIsNotGreen/splinter-encoder/resolve/main/gate.json
2.15 kB
| { | |
| "checkpoint": { | |
| "info": { | |
| "model": "experiments/encoder-suite/results/20261020/l3-tuned-v6", | |
| "params": 17389824, | |
| "params_m": 17.4, | |
| "dim": 384, | |
| "load_s": 0.1, | |
| "query_prefix": "" | |
| }, | |
| "dedup": { | |
| "n": 2141, | |
| "positives": 561, | |
| "at_0.92": { | |
| "precision": 1.0, | |
| "recall": 0.0463, | |
| "f1": 0.0886 | |
| }, | |
| "pos_p50": 0.764, | |
| "neg_p50": 0.3609, | |
| "separation": 0.4031, | |
| "best": { | |
| "f1": 0.8622, | |
| "precision": 0.8244, | |
| "recall": 0.9037, | |
| "threshold": 0.67 | |
| } | |
| }, | |
| "drift": { | |
| "n": 6533, | |
| "positives": 230, | |
| "auc": 0.943, | |
| "at_0.6": { | |
| "precision": 0.1065, | |
| "recall": 0.9435, | |
| "f1": 0.1914 | |
| }, | |
| "best": { | |
| "f1": 0.5728, | |
| "precision": 0.6484, | |
| "recall": 0.513, | |
| "threshold": 0.74 | |
| }, | |
| "signal_p50": 0.5576, | |
| "signal_min": 0.0354, | |
| "signal_max": 1.1474 | |
| }, | |
| "cost": { | |
| "ms_per_chunk": 1.06, | |
| "ms_per_100_chunks": 0.1 | |
| } | |
| }, | |
| "baseline": { | |
| "info": { | |
| "model": "sentence-transformers/paraphrase-MiniLM-L3-v2", | |
| "params": 17389824, | |
| "params_m": 17.4, | |
| "dim": 384, | |
| "load_s": 2.8, | |
| "query_prefix": "" | |
| }, | |
| "dedup": { | |
| "n": 2141, | |
| "positives": 561, | |
| "at_0.92": { | |
| "precision": 1.0, | |
| "recall": 0.0463, | |
| "f1": 0.0886 | |
| }, | |
| "pos_p50": 0.6864, | |
| "neg_p50": 0.3335, | |
| "separation": 0.3529, | |
| "best": { | |
| "f1": 0.7609, | |
| "precision": 0.6436, | |
| "recall": 0.9305, | |
| "threshold": 0.57 | |
| } | |
| }, | |
| "drift": { | |
| "n": 6533, | |
| "positives": 230, | |
| "auc": 0.9451, | |
| "at_0.6": { | |
| "precision": 0.082, | |
| "recall": 0.9565, | |
| "f1": 0.151 | |
| }, | |
| "best": { | |
| "f1": 0.5545, | |
| "precision": 0.6094, | |
| "recall": 0.5087, | |
| "threshold": 0.77 | |
| }, | |
| "signal_p50": 0.5813, | |
| "signal_min": 0.0391, | |
| "signal_max": 1.145 | |
| }, | |
| "cost": { | |
| "ms_per_chunk": 1.34, | |
| "ms_per_100_chunks": 0.1 | |
| } | |
| }, | |
| "verdict": { | |
| "dedup_f1": true, | |
| "drift_f1": true, | |
| "cost_ok": true, | |
| "pass": true | |
| }, | |
| "reported": { | |
| "dedup_best_f1": { | |
| "checkpoint": 0.8622, | |
| "baseline": 0.7609 | |
| }, | |
| "drift_best_f1": { | |
| "checkpoint": 0.5728, | |
| "baseline": 0.5545 | |
| }, | |
| "drift_auc": { | |
| "checkpoint": 0.943, | |
| "baseline": 0.9451 | |
| } | |
| } | |
| } |