Downloads · 30 days
0
ecoai-rag-encoder
sosa123454321/ecoai-rag-encoder
ecoai-rag-encoder is a sentence similarity model from sosa123454321. Use it when you need a score for how close two texts are. It is set up for sklearn. The card lists the license as apache-2.0.
Fitted retriever for FindExpert.ir ecoAI (not a 14B LoRA, not a MiniLM fork).
Access
Public
Updated Aug 30, 2026
Repo size
257 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.json227 KB · 58%
At a glance
- Task
- Sentence Similarity
- Library
- sklearn
- License
- apache-2.0
- Access
- Public
- Created
- Aug 29, 2026
- Updated
- Aug 30, 2026
- SHA
- 19e05afd
Datasets
Model card
From the Hugging Face model README
ecoai-rag-encoder
Fitted retriever for FindExpert.ir ecoAI (not a 14B LoRA, not a MiniLM fork).
This environment has ~2GB RAM and no GPU, so Qwen/E5 cannot be trained here. v2 = unicode word unigrams+bigrams, sublinear tf-idf, L2 cosine, extra Iran/grant recalls — still not a neural LoRA.
RAG Space that uses these weights: sosa123454321/ecoai-space
| File | Role |
|---|---|
encoder.joblib | sklearn TfidfVectorizer + doc matrix |
encoder.json | vocab + idf + sparse docs for the static Space |
Query the same way the Space does: vectorize the user text with this vocabulary, cosine vs documents, then write with Gemini on findexpert.ir (or future Qwen2.5-0.5B LoRA from ecoai-sft).
Dense upgrade later: encode passage: / query: with intfloat/multilingual-e5-small — do not replace this repo with forked MiniLM weights.
- Task
- Sentence Similarity
- Library
- sklearn
- License
- apache-2.0
- Languages
- fa, en
- Created
- Aug 29, 2026
- Updated
- Aug 30, 2026