The Q5KM GGUF from alexwkleung/Spark-X2.6-4B-Abliterated-GGUF with the peculiar-ragdoll Sharp-Spark chat template baked into the file as tokenizer.chattemplate, so runtimes pick it up without —chat-template-file`. This is a metadata-only edit. Weights are byte-identical to the source Q5KM — the tensor-data region of both files hashes to 57ce12c4…95f15e5. Exactly three GGUF keys differ from the source file: Everything else was copied verbatim with llama.cpp’s ggufnewmetadata.py at c7fc509. Spark-X2.6-4B (XHToken): dense 4.1B thinking model, spark25` architecture — hybrid attention (27 of 36 blocks use a 512-token sliding window, so the KV cache grows with only 9 full-attention layers), 16 Q / 4 KV heads of 256 dims, 131072 vocab. The abliterated build removed a refusal direction from 53 tensors with Heretic; see the source card for the method and full measurements. > Notice. The weights are a modified derivative: abliteration removes refusals, not the model’s knowledge or its failure modes — you are accountable for what you generate and for applicable law. XHToken did not produce, endorse, or review this build. Factual reliability is unchanged; only the signalling is gone.…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: cinnybun02
Теги: gguf, llama.cpp, abliterated, spark, sharp-template, conversational, en, zh
Лайков: 3 | Загрузок: 1,741
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
