Jiao hongbao's Trash

dataset pre-processingwe should format the prompt in a way that the model can recognize. we should refer the huggingface model documentation, to check the format we should transform the original dataset to. for Phi-2, it should be: 1234567where the model generates the text after "." . To encourage the model to write more concise answers, you can also try the following QA format using "Instruct: <prompt>\nOutput:"Instruct: Write a detailed analogy between mathematics...

in hyprland, it is a trouble about screenshots and clipboard. so this is the simple way to make a screenshot keybind. download a screenshot application first. 1sudo pacman -S grim #or others then write a keybind in your ~/.config/hypr/hyprland.conf 1bind = $mainmod, PRINT, exec, grim ~/Pictures/ and you can take shots with win + PrtSc play with arch homepageclick here to come back to play with archhomepage.

what I have done today: files link report click ISSCC-ideas click ISSCC-review click TensorCIM-ideas click MulTCIM-reivew click rep-powerpoint click and pdf version and the last version here. for now, I have done all thinkerlab research ability assessment.

The review of MulTCIM was completed this morning. here and thie afternoon I have to complete the innovation about two papers, and 3000 words report and at least 20 pages powerpoint, good luck. I have completed the innovative improvement to the An 88.36TOPS/W Bit-Level-Weight-Compressed LLM Accelerator with Cluster-Aligned INT-FP-GEMMLLM Accelerator with Cluster-Aligned INT-FP-GEMM and Bi-Dimensional Workflow Reformulationand Bi-Dimensional Workflow Reformulation. 23:54, I finish the...

关于为什么想写这篇blogps:...

I think I should start to complete the research assessment now. I should give some critical comments and innovate suggestion to these papers, and prepare to report recent research progress. here is the review of the An 88.36TOPS/W Bit-Level-Weight-Compressed LLM Accelerator with Cluster-Aligned INT-FP-GEMM and Bi-Dimensional Workflow Reformulation.

today I will read the ISSCC: An 88.36TOPS/W Bit-Level-Weight-Compressed Large-Language-Model Accelerator with Cluster-Aligned INT-FP-GEMM and Bi-Dimensional Workflow Reformulation the annotate is here.

one day, I want much more bigger space…so I need to replace my SSD with a 2TB one… _warning: mntx folder recommand to create at the path of “/“, and exclude it in the rsync step. that is recommanded, the core is to avoid recursively copy of your new folder, for example, if you create the mntx at /home/usr_name/mntx, when I copy old system to the /home/usr_name/mntx, it will create...

now it is 2025-5-21, 11:41. I initially wanted to start writing this record earlier, but due to some reasons, I begin to write it until today. 2025 has give me so many surprises, for example, the cancellation of Tsinghua’s summer camp(it has turn to exams inside the labs), the unexpected format of the spring selection at the Institute of Computing Technology(maybe because I haven’t follow closely), and the complete radio silence from Fudan’s summer camp.(not to mention the “of course it’s a...

continue to read the papers. I have read the MulTCIM: Digital Computing-in-Memory-Based Multimodal Transformer Accelerator With Attention-Token-Bit Hybrid Sparsity and TensorCIM: Digital Computing-in-Memory Tensor Processor With Multichip-Module-Based Architecture for Beyond-NN Acceleration the annotate is here: MulTCIM TensorCIM these two have something in common, such as cache-hit‘s idea. tomorrow I will continue to a new one, An 88.36TOPS/W Bit-Level-Weight-Compressed...