← Back to Explorer
Pending

Hy-MT2-1.8B (2026)

Hy-MT2-1.8B is a large language model released by Tencent, released under the apache-2.0 license, with a claimed knowledge cutoff of 2026-05-21. Its weights, configuration, and tokenizer files have been cryptographically hashed and are queued for on-chain attestation by Weight Registry.

Description

Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent's Hunyuan team, open-sourced May 21, 2026 alongside 7B and 30B-A3B siblings. It supports translation across 33 languages plus Chinese dialect/minority-language pairs, can be quantized to as little as 440MB, and is reported to outperform several mainstream commercial translation APIs despite its size.

Metadata

Type
LLM
Issuer
Tencent
License
apache-2.0
Size
3.80 GB
Knowledge cutoff
2026-05-21
Source
https://huggingface.co/tencent/Hy-MT2-1.8B
Revision
9a341cd1b679d3efd23b46e847b01745a71ed792

Hugging Face stats

28,477 downloads on Hugging Face · 1,222 likes · pipeline: translation · library: transformers

transformerssafetensorshunyuan_v1_densetext-generationtranslationzhenfrptes

Weight Hashes

Weights file
model.safetensors · 3.80 GB
SHA-25629e9117a44c79f81857613601968ff482d8a23c2d6736a1710bba9e5ca4762e5
SHA3-256357bb6cdff5a84d4360e01e5c2e80f77e1b614e0e742c66721d3315a4c734f91
BLAKE39c1b7e4a03f30589da48bb36c42b77048be3018159bed9bf1935b50c2df256e4
Config file
config.json · 1.32 KB
SHA-256da40c514cc74a5748a2e591b1b95fca4b7e94de05349abe4ea4164a82641de1a
SHA3-256e61ffee16543dcbf255174c7ba370cb9aed67c0581a27f1f0dfb5537f4a4a416
BLAKE39ee40996ed0352bc439b36b012d22005a2646a3446f7b74d1e20b67c676892a3
Tokenizer file
tokenizer.json · 9.09 MB
SHA-256b475bbef1b0b2fd57dcb865332b546475bd1ede2deb3bb91bafd0c047a8a530a
SHA3-2560318ae5d3646817d770b9c20dbd0732b0bba9a30750a28518b8fbe307e0e3402
BLAKE373fefe7983ddc07b18b60452afdc19857bf3fde18d9aca7a994a6f1c75a7828a

Verify it yourself

curl -L -o "model.safetensors" "https://huggingface.co/tencent/Hy-MT2-1.8B/resolve/9a341cd1b679d3efd23b46e847b01745a71ed792/model.safetensors"
sha256sum "model.safetensors"

Expected SHA-256: 29e9117a44c79f81857613601968ff482d8a23c2d6736a1710bba9e5ca4762e5