Lewdiculous/SLIDE-v2-GGUF-IQ-Imatrix

This repository hosts GGUF-IQ-Imatrix quants for NLPark/SLIDE-v2.

From quantization request #23.

Quants:

    quantization_options = [
        "Q4_K_M", "Q4_K_S", "IQ4_XS", "Q5_K_M", "Q5_K_S",
        "Q6_K", "Q8_0", "IQ3_M", "IQ3_S", "IQ3_XXS", "IQ2_M",
        "IQ2_S", "IQ3_XS", "IQ4_NL"
    ]

Using the latest of llama.cpp released at the time.

Card image:

Oringinal model card:

Shi-Ci Language Identify & Decode Expositor

7B, Multi-Language...

Prompt Format

Mistral-Instruct