Sentence Similarity
ONNX
Safetensors
English
ogma
embeddings
dense-retrieval
matryoshka
rag
agents
mteb
semantic-search
text-embeddings
text-embedding
vector-search
document-retrieval
similarity-search
classification
clustering
edge-ai
on-device
local-inference
efficient-ai
rag-retrieval
custom_code
Eval Results (legacy)
Commit History
-
docs: remove campaign-notes link (repo private)
Verified signature2fc50b4 -
docs: append MTEB(eng, v2) full-41 results (2026-07 eval campaign)
Verified signature08374c7
-
Upload README.md with huggingface_hub
SamVerified signature1d807a2 -
Upload README.md with huggingface_hub
SamVerified signature9dfff32 -
Upload README.md with huggingface_hub
SamVerified signatured553696 -
fix(docs): retrieval uses task=qry for both queries and docs
Empirical sweep (commit 5aa2fe6) shows (QRY, QRY) is best on retrieval. The published registry scores were measured under (QRY, QRY). Use that.5802663 -
docs: remove CPU inference benchmark table
990001e -
fix(docs): correct retrieval example to symmetric encoding
Empirical sweep (commit 5aa2fe6) showed (QRY, DOC) asymmetric routing underperforms symmetric (SYM, SYM) on these checkpoints by ~4pp. Updated Usage to show task="sym" for both queries and documents in retrieval, and migrated examples to AutoModel + AutoTokenizer.9b3afca -
Add OgmaTokenizerFast + model.embed() high-level API
- tokenization_ogma.py: PreTrainedTokenizerFast subclass that shifts content token ids by N_SPECIAL=7 (training-matched tokenization, no manual offset needed by callers) - tokenizer_config.json: wires AutoTokenizer to OgmaTokenizerFast - ogma_model.py: adds TaskToken class attr + embed(texts, task=) method so callers need only AutoModel + AutoTokenizer, no sys.modules digging108e5f2
-
Remove hedging from public model card
Hephaestus300b618 -
Clean public model card provenance wording
Hephaestusf97e884 -
Fix MTEB score and comparison hygiene
Verified signature7afa933
-
Enable AutoModel loading
Verified signature7d58306 -
Enable AutoModel loading
Verified signatureac330b8 -
Enable AutoModel loading
Verified signature7b8daf5 -
Enable AutoModel loading
Verified signature9b29bfe -
Enable AutoModel loading
Verified signature6b4e066 -
Enable AutoModel loading
Verified signaturebbae1b8 -
Use text embedding discovery tags
Verified signature1ac6e7e -
Expand use cases and explain Ogma name
Verified signaturef4b39dd -
Fix ogma-large MTEB status in model cards
Verified signature74bf6df -
Add ONNX export with parity report
Verified signaturead0de7b -
Add ONNX export with parity report
Verified signature20c6a97 -
Improve model card discoverability for embedding search
Verified signature71baec5
-
Expand safety eval: full toxicity + prompt injection tables (all classifiers, all metrics)
Verified signature668d483 -
Add comprehensive model card with MTEB benchmarks, MiniLM comparison, CPU inference benchmarks, and safety evaluation
Verified signature03c9ff6 -
chore: update license from MIT to CC-BY-NC-4.0
Verified signature727d314 -
Fix: relative imports for Hub loading, corrected model cards with accurate numbers and usage examples
Verified signature5d26ac1 -
Initial upload: ogma-mini embedding model
Verified signaturea20bf92 -
initial commit
Verified signature8f7c11e