infosave/Hy-MT2-cmf
translation model by infosave
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Tencent's Hy-MT2 translation family — 33 languages, instruction-following translation (terminology, style, placeholders, structured data) — as CMF files for cortiq: one memory-mapped file per model with the weights, the vendor tokenizer, the exact chat template and per-tensor hashes. The same file runs on the CPU, on Vulkan (NVIDIA / AMD / Intel), DX12 and Apple Metal; no Python, no PyTorch, no CUDA toolkit. Requires cortiq 0.7.0 or newer. Earlier runtimes do not know the hunyuanv1dense / hyv3 architectures (and 0.6.9 crashes on any 4-bit embedding — fixed in the same release). ¹ Twelve 512-token windows of wikitext-2 test, exact attention, the same yardstick every card on this account uses. The bf16-class reference for the 1.8B (q82f, not published) scores 24.77 — the 4-bit file sits within 10% (27.13 vs 24.77) of it. These are translation models: their perplexity on English encyclopedia prose is not what they were trained for, which…
Read the full model card ↗ · Preview checked 2026-10-29T22:09:21.603Z
Inside the original model card — Document outline
- Tencent Hy-MT2 — CMF (1.8B · 7B · 30B-A3B)
- Files
- What the runtime had to learn
- The 1.25-bit file, exactly
- Measured
- The MoE on any card (dynamic loading)
- Prompting
- Server
- Reproduce
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
infosave/Hy-MT2-cmf is a translation model repository published by infosave on Hugging Face. The source reports the cortiq library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- translation
- Library
- cortiq
- Recent downloads (30 days)
- 6,548
- Cumulative likes
- 2
- Hugging Face trending score
- 1
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-09-22T18:28:49.000Z
- Last modified
- 2026-09-23T05:05:27.000Z
Compatibility and lineage
Reported languages: zh, en, fr, pt, es, ja, tr, ru, ar, ko, th, it, de, vi, ms, id, tl, hi, pl, cs, nl, km, my, fa, gu, ur, te, mr, he, bn, ta, uk, bo, kk, mn, ug
Reported base models: tencent/Hy-MT2-1.8B, tencent/Hy-MT2-7B, tencent/Hy-MT2-30B-A3B
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-01T06:54:35.191Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.