— Model Architecture: GLM-5.3-Flash — Input: Text, Image — Output: Text — Model Optimizations: — Weight quantization: INT4 — Activation quantization: INT4 This is AWQ W4A16 (compressed-tensors) quantized checkpoint for vLLM. See below for license, disclaimer and more information about this model. > The abliterated (refusal-removed) build of zai-org/GLM-5.3-Flash > — a 320B / 18B-active Mixture-of-Experts model with hybrid linear + sparse attention, > 4-wide Manifold-Constrained Hyper-Connections, a native vision + video tower, an MTP > speculative head, and a 1M-token context. > > The refusal direction is baked directly into the official block-FP8 shards — same format, same > shard layout, same model.safetensors.index.json. Every tensor matches the base checkpoint in > name, dtype and shape, so this is a drop-in replacement for zai-org/GLM-5.3-Flash in any > stack that already serves it. > > On the -FP8 name: block-FP8 is the format Z.ai ships GLM-5.3-Flash in — the suffix names the > checkpoint’s own precision, not a quantization step we applied. There is no upstream BF16 release to > derive from, so this is the full-precision source as published. OrcaCode Review turns every…
Модальности:
Генерация текста
Области применения:
Логика и рассуждение Диалог / чат Вызов функций (Tool use)
Задача: Генерация текста
Автор: hell0ks
Теги: glm5_next, image-text-to-text, abliterated, glm, glm5, glm-5.3-flash, uncensored, ai-red-team
Лайков: 3 | Загрузок: 9,547
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
