Text Classification
Transformers
ONNX
Safetensors
English
llama
router
small-model
tiny-model
english
34m
query-routing
llm-router
model-routing
intent-classification
prompt-classification
sequence-classification
cpu
offline
local-ai
text-embeddings-inference
Instructions to use vrishv/router-34M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vrishv/router-34M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="vrishv/router-34M")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("vrishv/router-34M") model = AutoModelForSequenceClassification.from_pretrained("vrishv/router-34M", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
Today
-
router v3: on the IAM-free Viveka, wider data, 94.1% test, now CC BY-SA 4.0
Verified signaturef0f95b9
5 days ago
-
Router v2: more and shorter maths, cleaner code examples
Verified signature17a87c7 -
Router v1: Viveka-34M sorting questions into 4 buckets
Verified signature37a6f07