Instructions to use minishlab/potion-base-4M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Model2Vec
How to use minishlab/potion-base-4M with Model2Vec:
from model2vec import StaticModel model = StaticModel.from_pretrained("minishlab/potion-base-4M") embeddings = model.encode(["It's dangerous to go alone!", "It's a secret to everybody."]) print(embeddings.shape) - sentence-transformers
How to use minishlab/potion-base-4M with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("minishlab/potion-base-4M") 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
Add full-test ArguAna CPU replication with reproducible traces
#1
by dmytro-nasyrov - opened
.eval_results/pharos-arguana-cpu-20261112.yaml
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: mteb/arguana
|
| 3 |
+
task_id: ArguAna_default_test
|
| 4 |
+
revision: c22ab2a51041ffd869aaddef7af8d8215647e41a
|
| 5 |
+
value: 39.561
|
| 6 |
+
date: "2026-11-12"
|
| 7 |
+
source:
|
| 8 |
+
url: https://pharosproduction.com/wp-content/uploads/research/potion-arguana-20261112/pharos-arguana-potion-base-4m-2026-11-12-report.pdf
|
| 9 |
+
name: Pharos Production CPU replication report
|
| 10 |
+
user: pharosproduction
|
| 11 |
+
notes: "Full ArguAna test: 1406 queries, 8674 corpus documents; nDCG@10 x 100; MTEB 2.27.10; static CPU embeddings; model revision 9b3cff412d30be9ae8603fe10224c224f3401869; no generation or training. Independent community replication, not upstream verified."
|