Downloads · 30 days
9
24% of all-time downloads
tor-simt-gemma-2b-waitk
unswnlporg/tor-simt-gemma-2b-waitk
tor-simt-gemma-2b-waitk is a machine learning model from unswnlporg. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Experiment gemma2bwaitk from the Teacher-Free Read/Write Annotation for Simultaneous Machine Translation project.
All-time downloads
37
Public
Parameters
5.1B
10.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors10.2 GB · 99%
At a glance
- License
- mit
- Model type
- gemma4
- Access
- Public
- Created
- Sep 7, 2026
- Updated
- Sep 7, 2026
- SHA
- 73ec000c
Model card
From the Hugging Face model README
gemma_2b_waitk
Experiment gemma_2b_waitk from the Teacher-Free Read/Write Annotation for Simultaneous
Machine Translation project.
Recipe
- Backbone:
google/gemma-4-E2B-it - Corpus:
curated - Annotator:
none - Criterion:
wait-k(τ = 0) - Latencies: ['low', 'medium', 'high']
Files in this repo
config.yaml— the exact experiment config that produced this run.manifest.json— git sha, hostname, GPUs, timestamps.logs/— per-stage stdout+stderr frombin/run.eval/— every landed eval-JSON cell (hypothesis, reference, AL, BLEU).annotate/— per-directionmatrices.jsonl(divergence matrices) produced by this backbone as annotator.source_pool.json— the corpus rows the matrices index into ({index, source, target, src_lang, tgt_lang, latency, source_chunks, target_chunks, _corpus}). Matrices are unjoinable without this file — records only carryindex.- SFT checkpoint (
*.safetensors+ tokenizer).
Reproduce
git clone https://github.com/dipankarsrirag/simt-tor-26.git
cd simt-tor-26
cp .simtrc.example .simtrc # edit paths for your setup
bin/run configs/gemma_2b_waitk.yaml --ngpus N
Git commit at time of run: unknown
- Type
- gemma4
- License
- mit
- Languages
- ar, de, en, vi
- Created
- Sep 7, 2026
- Updated
- Sep 7, 2026