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
Download run.json from vrishv/router-34M: direct link, hf CLI and curl.
- Browser
- Download file 158 Bytes
-
https://huggingface.co/vrishv/router-34M/resolve/main/run.json
- Command line
-
hf download hf://vrishv/router-34M/run.json
-
curl -L -o run.json https://huggingface.co/vrishv/router-34M/resolve/main/run.json
158 Bytes
| {"version": 3, "val_accuracy": 0.9485887096774194, "test_accuracy": 0.9405541561712847, "tricky_right": "22 of 27", "lr": 7e-05, "epochs": 5, "best_epoch": 3} |