# CPU Optimization

A fasttext-based text classifier for categorizing text into mathematical or non-mathematical classes, suitable for LLM pre-training data organization

A mental health counseling dialogue model fine-tuned based on LLaMA-3.2-1B, capable of running on CPU and low-memory devices

A lightweight FastText-based classifier for evaluating the educational value of web content, optimized for CPU processing speed

Provides quantized and non-quantized embedding models in GGUF format, specifically designed for llama.cpp. Significantly improves speed when running on CPUs, with moderate acceleration for large models on GPUs.

Provides GGUF format quantized and non-quantized embedding models, designed specifically for llama.cpp, outperforming transformers with significant speed improvements on CPUs

A medical domain chatbot based on the Llama-2-7B-Chat-GGML model, specializing in answering medical-related questions and providing medical text generation capabilities

A GGUF format model based on the 7B version of llama2, designed for prompt generation and compatible with CPU environments

CPU-optimized Korean processing pipeline with complete NLP functions including tokenization, part-of-speech tagging, dependency parsing, named entity recognition, etc.

CPU-optimized Romanian natural language processing model, including tokenization, part-of-speech tagging, dependency parsing, named entity recognition, and other functions

A CPU-optimized multilingual named entity recognition model supporting location, organization, person, and other entity types

CPU-optimized Lithuanian processing pipeline with complete NLP functions including tokenization, POS tagging, dependency parsing, and named entity recognition

CPU-optimized Russian processing pipeline including token classification, dependency parsing, named entity recognition and other NLP tasks