开启时会模糊预览图，关闭后正常显示
Oh, i forgot, 3% applied materials (MP). It's the only position of mine that's not a tech company, but I just figured the entire supply chain was being bought up and China was being sussy baka + I traded it in 2021 alongside NMM, Gamestop and Palantir. Anyway, up 30% so far.
oklo has a gap down at 80-110. decent accumulation zone is 50s-80s and lower, which we may or may not see bc it's got more contracts since that time. until then i'm just farming selling calls on my shares, and @zephyr_z9 has had some good picks lately.
Gumroad in India: Feb 16-20! Save the date
2027*
https://t.co/LmN6sBLkwj it turns out if you take code context engineering very, very, very seriously... it's useful for humans too
launched
btw if you liked DeepWiki, you're gonna love what's coming next for repos like this. trying to see what we can open source too.
https://t.co/LmN6sBLkwj it turns out if you take code context engineering very, very, very seriously... it's useful for humans too
Excited to release new repo: nanochat! (it's among the most unhinged I've written). Unlike my earlier similar repo nanoGPT which only covered pretraining, nanochat is a minimal, from scratch, full-stack training/inference pipeline of a simple ChatGPT clone in a single, dependency-minimal codebase. You boot up a cloud GPU box, run a single script and in as little as 4 hours later you can talk to your own LLM in a ChatGPT-like web UI. It weighs ~8,000 lines of imo quite clean code to: - Train the tokenizer using a new Rust implementation - Pretrain a Transformer LLM on FineWeb, evaluate CORE score across a number of metrics - Midtrain on user-assistant conversations from SmolTalk, multiple choice questions, tool use. - SFT, evaluate the chat model on world knowledge multiple choice (ARC-E/C, MMLU), math (GSM8K), code (HumanEval) - RL the model optionally on GSM8K with "GRPO" - Efficient inference the model in an Engine with KV cache, simple prefill/decode, tool use (Python interpreter in a lightweight sandbox), talk to it over CLI or ChatGPT-like WebUI. - Write a single markdown report card, summarizing and gamifying the whole thing. Even for as low as ~$100 in cost (~4 hours on an 8XH100 node), you can train a little ChatGPT clone that you can kind of talk to, and which can write stories/poems, answer simple questions. About ~12 hours surpasses GPT-2 CORE metric. As you further scale up towards ~$1000 (~41.6 hours of training), it quickly becomes a lot more coherent and can solve simple math/code problems and take multiple choice tests. E.g. a depth 30 model trained for 24 hours (this is about equal to FLOPs of GPT-3 Small 125M and 1/1000th of GPT-3) gets into 40s on MMLU and 70s on ARC-Easy, 20s on GSM8K, etc. My goal is to get the full "strong baseline" stack into one cohesive, minimal, readable, hackable, maximally forkable repo. nanochat will be the capstone project of LLM101n (which is still being developed). I think it also has potential to grow into a research harness, or a benchmark, similar to nanoGPT before it. It is by no means finished, tuned or optimized (actually I think there's likely quite a bit of low-hanging fruit), but I think it's at a place where the overall skeleton is ok enough that it can go up on GitHub where all the parts of it can be improved. Link to repo and a detailed walkthrough of the nanochat speedrun is in the reply.
GitHub repo: https://t.co/Cpm3Dc44rY A lot more detailed and technical walkthrough: https://t.co/YmHaZfNjcJ Example conversation with the $100, 4-hour nanochat in the WebUI. It's... entertaining :) Larger models (e.g. a 12-hour depth 26 or a 24-hour depth 30) quickly get more coherent.
Crete, Greece
Edinburgh, UK
