Tinker-Stack/DeepSeek-V4-Flash-0731-REAP-150b-TQ3_4S-GGUF - Каталог нейросетей
Генерация текста

Tinker-Stack/DeepSeek-V4-Flash-0731-REAP-150b-TQ3_4S-GGUF

Добавлено:
Tinker-Stack/DeepSeek-V4-Flash-0731-REAP-150b-TQ3_4S-GGUF

A custom, selectively-quantized GGUF of the DeepSeek-V4-Flash-0731 architecture, pruned to the 150B «REAP» variant, quantized with a hand-tuned per-tensor recipe and wrapped in the TurboQuant TQ34S container from the turbo-tan/llama.cpp-tq3` fork. This is not a plain uniform quant. It is the result of iterative quantization on a 3× Turing GPU box, and the recipe reflects a specific, measured trade-off: maximize context length (256K) while holding wikitext-2 perplexity within noise of the IQ3_XXS baseline that proved to be the local optimum for this model. This quant vs. the models it derives from. Metrics per the REAP benchmarks: GSM8K exactmatch, MATH-500 mathverify, HumanEval+/MBPP+ pass@1plus` (greedy, n=1). ᵃ Thinking mode (reasoningeffort=high + answer headroom floor, §7 pitfall 8). Base and FP8 reference scores are from the REAP model card, run with thinking off**; in matched no-thinking protocol this build scores 0.696 (MATH-500) and 0.6524 (HumanEval+). Full methodology, the both-protocols matrix, and spiral rates: §4. The quantization itself costs ~nothing: no-thinking GSM8K is within stderr of the FP8 checkpoint (−0.68), MATH-500 is −1.8, MBPP+ is +10.3 above. The…

Модальности:
Генерация текста

Области применения:
Генерация кода Логика и рассуждение Диалог / чат Вызов функций (Tool use) Мультиязычность


Задача: Генерация текста
Автор: Tinker-Stack
Теги: llama.cpp, gguf, experimental, deepseek, deepseek-v4, moe, turboquant, tq3_4s
Лайков: 3  |  Загрузок: 1,925

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.