Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

fix(docs): retrieval uses task=qry for both queries and docs

docs: remove CPU inference benchmark table

fix(docs): correct retrieval example to symmetric encoding

Add OgmaTokenizerFast + model.embed() high-level API

Remove hedging from public model card

Clean public model card provenance wording

Fix MTEB score and comparison hygiene

Enable AutoModel loading

Enable AutoModel loading

Enable AutoModel loading

Enable AutoModel loading

Enable AutoModel loading

Enable AutoModel loading

Use text embedding discovery tags

Expand use cases and explain Ogma name

Fix ogma-large MTEB status in model cards

Add ONNX export with parity report

Add ONNX export with parity report

Improve model card discoverability for embedding search

Expand safety eval: full toxicity + prompt injection tables (all classifiers, all metrics)

Add comprehensive model card with MTEB benchmarks, MiniLM comparison, CPU inference benchmarks, and safety evaluation

chore: update license from MIT to CC-BY-NC-4.0

Fix: relative imports for Hub loading, corrected model cards with accurate numbers and usage examples

Initial upload: ogma-large embedding model

initial commit