This is stars and forks stats for /qwopqwop200/GPTQ-for-LLaMa repository. As of 28 Apr, 2024 this repository has 2651 stars and 429 forks.
GPTQ-for-LLaMA I am currently focusing on AutoGPTQ and recommend using AutoGPTQ instead of GPTQ for Llama. 4 bits quantization of LLaMA using GPTQ GPTQ is SOTA one-shot weight quantization method It can be used universally, but it is not the fastest and only supports linux. Triton only supports Linux, so if you are a Windows user, please use WSL2. News or Update AutoGPTQ-triton, a packaged version of GPTQ with triton, has been integrated into AutoGPTQ. Result LLaMA-7B(click me) LLaMA-7B Bits group-size memory(MiB) Wikitext2 checkpoint...
GPTQ-for-LLaMA I am currently focusing on AutoGPTQ and recommend using AutoGPTQ instead of GPTQ for Llama. 4 bits quantization of LLaMA using GPTQ GPTQ is SOTA one-shot weight quantization method It can be used universally, but it is not the fastest and only supports linux. Triton only supports Linux, so if you are a Windows user, please use WSL2. News or Update AutoGPTQ-triton, a packaged version of GPTQ with triton, has been integrated into AutoGPTQ. Result LLaMA-7B(click me) LLaMA-7B Bits group-size memory(MiB) Wikitext2 checkpoint...
repo | techs | stars | weekly | forks | weekly |
---|---|---|---|---|---|
guillaumekln/faster-whisper | Python | 5k | 0 | 357 | 0 |
aws/aws-eks-best-practices | PythonGoDockerfile | 1.6k | 0 | 391 | 0 |
Berkanktk/CyberSecurity | PythonShellC++ | 525 | 0 | 33 | 0 |
KohakuBlueleaf/LyCORIS | Python | 1.5k | +21 | 93 | +1 |
kevinjycui/DesmosBezierRenderer | PythonHTML | 466 | +5 | 94 | +1 |
IHP-GmbH/IHP-Open-PDK | PythonHTMLMATLAB | 201 | 0 | 15 | 0 |
innnky/emotional-vits | Jupyter NotebookPython | 1k | 0 | 148 | 0 |
microsoft/visual-chatgpt | PythonHTMLDockerfile | 34.2k | 0 | 3.3k | 0 |
Azure-Samples/azure-search-openai-demo | PythonTypeScriptBicep | 3.8k | 0 | 2.2k | 0 |
butaixianran/Stable-Diffusion-Webui-Civitai-Helper | PythonJavaScriptCSS | 2k | +13 | 232 | +1 |