LFM2‑350M‑ENJP‑MT is a fine‑tuned LFM2‑350M checkpoint that delivers near real‑time, bidirectional Japanese/English translation for short‑to‑medium inputs with quality comparable to models over ten times larger, as illustrated across everyday, technical, business, and news domains, and emphasizes collaborative human‑AI use.
Description in other languages
Statistics
Statistics as of Nov 16, 2026
Hugging Face downloads (last 30 days)
1,000
Hugging Face likes
99
Listed
Sep 9, 2025
Downloads (30-day window) over time
Show as a table
| Month | DL (30d) |
|---|---|
| Dec 2025 | 5,000 |
| Jan 2026 | — |
| Feb 2026 | — |
| Mar 2026 | — |
| Apr 2026 | 1,000 |
| May 2026 | — |
| Jun 2026 | — |
| Jul 2026 | — |
| Aug 2026 | — |
| Sep 2026 | — |
| Oct 2026 | — |
| Nov 2026 | 1,000 |
Downloads over the 30 days before the last snapshot of each month.
Popular in the same category
- opus-mt-ja-enHelsinki-NLP37kJapanese‑to‑English Transformer‑Align MT model from the Opus corpus, using normalization and SentencePiece preprocessing, achieves 41.7 BLEU and 0.589 chr‑F on the Tatoeba test set.
- vntl-llama3-8b-v2-gguflmg-anon20kA LLaMA 3 Youko qlora fine‑tune built on a new VNTL dataset, optimized for accurate, literal translations of Japanese visual novels to English without chat mode, using the default LLaMA 3 prompt and recommending neutral sampling (temperature 0, no repetition penalty).
- Sugoi-14B-Ultra-GGUFsugoitoolkit10kSugoi LLM 14B Ultra (GGUF) is a Japanese‑to‑English translation model with a BLEU score of 21.38—nearly double its prior 13.67—excel at RPG‑Maker bracketed text, strong prompt adherence, and JSON output for interactive chat UIs.
- LFM2-350M-ENJP-MT-GGUFLiquidAI5kFine‑tuned, GGUF‑quantized LFM2‑350M checkpoint for near real‑time bi‑directional Japanese‑English translation of short‑to‑medium text, usable via llama.cpp.
- fugumt-ja-enstaka4kFuguMT is a Japanese‑to‑English Marian‑NMT translation model built with transformers and SentencePiece, scoring 39.1 BLEU on Tatoeba.
- fugumt-en-jastaka4kFuguMT is a Marian‑NMT based English‑to‑Japanese translation model built with Hugging Face Transformers and SentencePiece, achieving a BLEU score of 32.7 on Tatoeba.
Resources in similar research fields
LibreTranslateLibreTranslate17kFree and Open Source Machine Translation API. Self-hosted, offline capable and easy to setup.MultilingualShared: Machine translation
seamless_communicationfacebookresearch12kFoundational Models for State-of-the-Art Speech and Text Translation.MultilingualShared: Machine translation
argos-translateargosopentech6.5kOpen-source offline translation library written in Python.MultilingualShared: Machine translation
Opus-MTHelsinki-NLP866Open neural machine translation models and web services.MultilingualShared: Machine translation
Hy-MTTencent-Hunyuan829Hunyuan Translation Model Version 1.5, including a 1.8B translation model (HY-MT1.5-1.8B) and a 7B translation model (HY-MT1.5-7B).MultilingualShared: Machine translation
Hy-MT2Tencent-Hunyuan679Hy-MT2 is a family of "fast-thinking" multilingual translation models designed for complex real-world scenarios, in three sizes: 1.8B, 7B, and 30B-A3B.MultilingualShared: Machine translation