Downloads · 30 days
3.2K
41% of all-time downloads
xCloudinfo/Gemma-4-26B-A4B-TAIDE-zhTW-abliterated-GGUF
Gemma-4-26B-A4B-TAIDE-zhTW-abliterated-GGUF is a image-text-to-text model from xCloudinfo. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
云碩科技 · xCloudinfo · 系列:降低過度拒絕 · Abliterated
Downloads · 30 days
3.2K
41% of all-time downloads
All-time downloads
7.8K
Public
Repo size
128 GB
Likes
0
Public
Click a slice to open those files.
.gguf111 GB · 100%
From the Hugging Face model README
云碩科技 · xCloudinfo · 系列:降低過度拒絕 · Abliterated
使用前提 本模型以合法、且在使用者獲授權範圍內使用為前提製作與發布。經abliteration降低模型的 過度拒絕傾向,供資安研究、文件與資料分析、領域問答、紅隊評估、創作等正當工作使用。 使用者須在中華民國法律及所適用法規範圍內使用,並對一切用途與後果負完全責任; 不得用於任何違法或造成他人危害之用途。
xCloudinfo/Gemma-4-26B-A4B-TAIDE-zhTW
的降低過度拒絕版GGUF,含視覺投影器(mmproj),可圖文對話。
六階量化 Q8_0 / Q6_K / Q5_K_M / Q4_K_M / IQ4_XS / IQ2_M + imatrix + 視覺投影器(mmproj)。
llama-server -m model-Q4_K_M.gguf \
--mmproj mmproj-Gemma-4-26B-A4B-TAIDE-zhTW-f16.gguf -c 4096 -ngl 99
純文字可省略
--mmproj。Q4_K_M部署首選;Q8_0/Q6_K追品質;IQ4_XS/IQ2_M省資源。
google/gemma-4-26B-A4B-it:Apache-2.0 + Google
Gemma 4 License(含Prohibited Use Policy)。云碩科技(xCloudinfo Corp. Limited)專注於地端私有化人工智慧解決方案。xVITA是云碩自研模型的品牌名稱。
其他模型請見 https://hf.co/xCloudinfo。
由 云碩科技xCloudinfo於自有AI算力資源池製作。
xCloudinfo (云碩科技) · Series: Reduced over-refusal · Abliterated
Condition of use This model was built and released on the premise that it is used lawfully and within the scope the user is authorized for. Abliteration reduces the model's tendency toward over-refusal, for legitimate work such as security research, document and data analysis, domain Q&A, red-team evaluation, and creative writing. Users must use it within the laws of the Republic of China (Taiwan) and applicable regulations, and bear full responsibility for all uses and consequences; it must not be used for any unlawful purpose or to harm others.
The reduced over-refusal GGUF of xCloudinfo/Gemma-4-26B-A4B-TAIDE-zhTW,
including the vision projector (mmproj) for image-and-text chat.
Six quantization tiers Q8_0 / Q6_K / Q5_K_M / Q4_K_M / IQ4_XS / IQ2_M + imatrix + vision projector (mmproj).
llama-server -m model-Q4_K_M.gguf \
--mmproj mmproj-Gemma-4-26B-A4B-TAIDE-zhTW-f16.gguf -c 4096 -ngl 99
For text only,
--mmprojcan be omitted. Q4_K_M is the first choice for deployment; Q8_0/Q6_K for quality; IQ4_XS/IQ2_M to save resources.
google/gemma-4-26B-A4B-it: Apache-2.0 + Google
Gemma 4 License (including the Prohibited Use Policy).xCloudinfo Corp. Limited (云碩科技) builds on-premises, private AI solutions. xVITA is xCloudinfo's in-house model brand.
More models: https://hf.co/xCloudinfo
Built by xCloudinfo (云碩科技) on its own AI compute pool.