GPTQ - a kaitchup Collection

kaitchup 's Collections

Qwen2.5 Quantized

Opus Translation Datasets

GPTQ

Yi

Contaminated Mistral 7B and TinyLlama

Llama 3 70B ExLlamaV2 (bpw: 4.0, 3.5, 3.0, 2.5, and 2.18)

[Basics] Quantized Phi-3

[Basics] AutoRound: Llama 3

Quantized Llama 3.1

The Minitron Models and Their Teachers, Quantized

Minivoc

GPTQ

updated May 6

Llama 2 7B, 13B, Llama 3 8B, and Mistral 7B quantized with GPTQ in 2-bit, 3-bit, 4-bit and 8-bit with GPTQ.