Tag:llm
All the articles with the tag "llm".
如何做 continued pre-train
Posted on:July 4, 2023 at 12:00 AM介绍一下 continued pre-train
WizardLM(Coder) 和 Ocra 的一些理解
Posted on:July 22, 2023 at 12:00 AM介绍一下最近看到的两篇关于 SIFT 数据相关的非常好的论文 WizardLM(WizardCoder) 和 Ocra，以及我对这个问题的一些思考
CodeLLM Training Recipe
Posted on:July 26, 2023 at 12:00 AM一个偏综述的文章，总结 codeLLM 相关 paper 从 data collection 到 training 中间的一些细节
RoPE and Length Scaling
Posted on:August 10, 2023 at 12:00 AMIntroduce some basic concepts of Position Encoding, RoPE and length extrapolation related it.
Benchmark for LLM Inference
Posted on:August 20, 2023 at 12:00 AMIntroduce some metrics for LLM inference benchmarking
GPTQ Math Derivation
Posted on:September 9, 2023 at 12:00 AMThis blog post traces the development of GPTQ, starting from its roots in OBD, through OBS, and finally to OBC.
GPTQ Code Implementation
Posted on:September 18, 2023 at 12:00 AMThis blog post delved into the code implementation of the GPTQ quantization process, using the Llama model as a case study.
LLM Quantization Review
Posted on:October 2, 2023 at 12:00 AMThis blog post provides an overview of the fundamental concepts of quantization, as well as a review of mainstream quantization methods in the context of LLMs.
SmoothQuant and AWQ
Posted on:October 8, 2023 at 12:00 AMThis blog post compares *SmoothQuant* and *AWQ* differences and their code implementation.
8-bit KV Cache
Posted on:January 24, 2024 at 12:00 AMThis blog introduces KV Cache quantization in LLM inference.