AhmedReda25300/Ara-JEV - Каталог нейросетей
Генерация текста

AhmedReda25300/Ara-JEV

Добавлено:
AhmedReda25300/Ara-JEV

Ara-JEV is a compact Arabic decision model fine-tuned from Qwen3.5-0.8B. Given a short state, a question, and optional candidate choices, it selects the best answer label. This repository contains a standalone merged checkpoint: the trained LoRA weights have been merged into the base model. You do not need to load a separate adapter. The held-out test set contains 10,419 examples. The results below use constrained candidate-label scoring: for each example, the evaluator scores the allowed labels and selects the highest-scoring one. This measures decision accuracy when the candidate labels are known; it is not free-form generation accuracy. The primary evaluation prompt does not include dialect metadata. The yes/no subset is the main weakness. Consider this when choosing the model for arithmetic-heavy or binary decisions. A separate 100-example sample was benchmarked using vLLM 0.32.0 on an NVIDIA A40. Requests were sequential, used bfloat16 and constrained candidate labels, and ran locally after five warm-up requests. These are local, single-request measurements; latency and throughput vary with hardware, prompt length, concurrency, and serving configuration. The sample’s 93/100…

Модальности:
Генерация текста

Области применения:
Диалог / чат


Задача: Генерация текста
Автор: AhmedReda25300
Теги: qwen3_5, image-text-to-text, arabic, qwen3.5, decision-making, merged-lora, conversational, custom_code
Лайков: 3  |  Загрузок: 1,186

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.