IntelLabs/sqft-qa-sparsepeft-mistral-7b-v0.3-50-gptq-math-heu

— Base Model: IntelLabs/sqft-mistral-7b-v0.3-50-base-gptq — Sparsity: 50% — Quantization: INT4 (GPTQ) — Finetune Method: SQFT + QA-SparsePEFT — Finetune data: 10K instruction-following math reasoning training dataset from LLM-Adapters (math_10k.json) — Sub-Adapter: Heuristic Refer to our repo for the environment information to run this command. Repository: https://github.com/IntelLabs/Hardware-Aware-Automated-Machine-Learning/tree/main/SQFT Paper: — SQFT: Low-cost Model Adaptation in Low-precision Sparse Foundation Models — Low-Rank Adapters Meet Neural Architecture Search for LLM Compression

Модальности:
Генерация текста

Области применения:
Математика

Задача: Генерация текста
Автор: IntelLabs
Теги: mistral, en, text-generation-inference, endpoints_compatible, 4-bit, gptq
Лайков: 3  |  Загрузок: 20

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.