Downloads · 30 days
146
26% of all-time downloads
sappho192/MiLMMT-46-1B-v0.1-ko-en-ja-pruned-130k-imatrix-Q4_K_M-GGUF
MiLMMT-46-1B-v0.1-ko-en-ja-pruned-130k-imatrix-Q4_K_M-GGUF is a translation model from sappho192. Use it when you need text moved from one language to another. It is set up for gguf. The card lists the license as gemma.
This repository provides an unofficial GGUF derivative of xiaomi-research/MiLMMT-46-1B-v0.1 for local Korean, English, and Japanese translation.
Downloads · 30 days
146
26% of all-time downloads
All-time downloads
563
Public
Repo size
804 MB
Likes
0
Public
Click a slice to open those files.
.gguf804 MB · 100%
From the Hugging Face model README
This repository provides an unofficial GGUF derivative of
xiaomi-research/MiLMMT-46-1B-v0.1
for local Korean, English, and Japanese translation.
The model was not fine-tuned. It was produced by retaining a 130k-token
ko/en/ja-focused vocabulary, applying importance-matrix calibration, and using
a mixed quantization policy: Q4_K_M by default, with Q8_0 retained for
ffn_gate and ffn_up tensors in transformer blocks 16–25.
milmmt-pruned-130k-bf16-imatrix-mix-late16-25-ffngateupq8-Q4_K_M.gguf5f781fdc9a685212dba3244b7cf2df39625776066043408f769549195f018b0dAgainst the local MiLMMT Q8_0 baseline, this model achieved a 0.995182
average chrF++ ratio and a 0.991064 worst-direction ratio on the full
FLORES+ dev ko/en/ja evaluation. It also passed an independent 100-row
devtest check.
This is the current recommended low-VRAM balanced variant from this experiment. It is not the absolute smallest evaluated GGUF, nor the absolute highest-scoring variant; smaller candidates failed the held-out quality gate, while the Q8_0 baseline is substantially larger.
Use the MiLMMT raw translation prompt format:
Translate this from <source language> to <target language>:
<source language>: <text>
<target language>:
This model is intended for translation, not general chat or reliable use in languages outside Korean, English, and Japanese. It is an independent derivative and is not affiliated with or endorsed by Xiaomi or Google.
Gemma is provided under and subject to the Gemma Terms of Use found at ai.google.dev/gemma/terms