Text Classification
Transformers
Safetensors
Laya
Arabic
modernbert
feature-extraction
arabic
information-retrieval
reranking
rag
custom_code
Eval Results (legacy)
Instructions to use Wouze/laya-ara-rag with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Wouze/laya-ara-rag with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Wouze/laya-ara-rag", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("Wouze/laya-ara-rag", trust_remote_code=True) model = AutoModel.from_pretrained("Wouze/laya-ara-rag", trust_remote_code=True, device_map="auto") - Laya
How to use Wouze/laya-ara-rag with Laya:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Fix links in FINDINGS.md
Browse files- FINDINGS.md +1 -1
FINDINGS.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
# Additional experiments
|
| 2 |
|
| 3 |
-
Companion note to **laya-ara-rag**. Stock is `convaiinnovations/laya-multilingual`. NLU card: [`laya-ara`](https://huggingface.co/Wouze/laya-ara). Tables: [`RESULTS.md`](RESULTS.md). JSON: [`
|
| 4 |
|
| 5 |
RAG is top-1 among *k*≤12, not nDCG@10.
|
| 6 |
|
|
|
|
| 1 |
# Additional experiments
|
| 2 |
|
| 3 |
+
Companion note to **laya-ara-rag**. Stock is `convaiinnovations/laya-multilingual`. NLU card: [`laya-ara`](https://huggingface.co/Wouze/laya-ara). Tables: [`RESULTS.md`](RESULTS.md). JSON: [`rag_all_benches.json`](https://huggingface.co/Wouze/laya-ara-rag/blob/main/results/rag_all_benches.json) · [`all_cards.json`](https://huggingface.co/Wouze/laya-ara-rag/blob/main/results/all_cards.json).
|
| 4 |
|
| 5 |
RAG is top-1 among *k*≤12, not nDCG@10.
|
| 6 |
|