Translation
Transformers
ONNX
Safetensors
Transformers.js
t5
text2text-generation
seq2seq
browser-ml
timers
synthetic-data
text-generation-inference
Instructions to use Satansdeer/timmy-t2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Satansdeer/timmy-t2 with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="Satansdeer/timmy-t2")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Satansdeer/timmy-t2") model = AutoModelForSeq2SeqLM.from_pretrained("Satansdeer/timmy-t2") - Transformers.js
How to use Satansdeer/timmy-t2 with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('translation', 'Satansdeer/timmy-t2'); - Notebooks
- Google Colab
- Kaggle
Browser Runtime Artifact
This folder contains the production browser artifact for Timmy T2 v0.1.0.
The Timey app uses Transformers.js 4.2.0 for tokenization and ONNX Runtime Web 1.26.0-dev.20260416-b7804b056c for explicit encoder/decoder inference.
Files:
onnx/encoder_model_quantized.onnx: dynamic q8 encoderonnx/decoder_model_quantized.onnx: q4 decoder- tokenizer and config files copied from the production browser model directory
The browser artifact is validated through the app's parser and production smoke checks. See ../release_manifest.json for hashes, sizes, and eval summaries.