Text Generation
sentence-transformers
Indonesian
English
chatbot
retrieval
hybrid-search
bm25
tfidf
sbert
mpnet
use
fuzzy-matching
indonesian
english
conversational
context-aware
multilingual
caca
Eval Results (legacy)
Instructions to use Lyon28/Caca-Chatbot-V2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Lyon28/Caca-Chatbot-V2 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Lyon28/Caca-Chatbot-V2") 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
| { | |
| "model_name": "CACA - Contextual Adaptive Conversational AI", | |
| "version": "1.0.0", | |
| "dataset": "Lyon28/Caca-Behavior", | |
| "repo_name": "Lyon28/Caca-Chatbot-V2", | |
| "techniques": { | |
| "bm25": 0.12, | |
| "tfidf": 0.1, | |
| "sbert_mini": 0.15, | |
| "sbert_mpnet": 0.2, | |
| "use": 0.1, | |
| "fuzzy": 0.1, | |
| "jaccard": 0.05, | |
| "ngram": 0.05, | |
| "pattern": 0.08, | |
| "keyword_boost": 0.05 | |
| }, | |
| "context": { | |
| "enabled": true, | |
| "max_history": 5, | |
| "weight": 0.15 | |
| }, | |
| "multilang": { | |
| "enabled": true, | |
| "supported": [ | |
| "id", | |
| "en" | |
| ] | |
| } | |
| } |