minor typo fixes

README.md

@@ -8,7 +8,7 @@ This repo is a full-stack implementation of an LLM like ChatGPT in a single, cle
 
 ## Talk to it
 
-To get a sense of the endpoint of this repo, you can currently find [nanochat d32](https://github.com/karpathy/nanochat/discussions/8) hosted on [nanochat.karpathy.ai](https://nanochat.karpathy.ai/). "d32" means that this model has 32 layers in the Transformer neural network. This model has 1.9 billion parameters, it was trained on 38 billion tokens by simply running the single script [run1000.sh](run1000.sh), and the total cost of training was ~$800 (about 33 hours training time on 8XH100 GPU node). While today this is enough to outperform GPT-2 of 2019, it falls dramatically short of moden Large Language Models like GPT-5. When talking to these micro models, you'll see that they make a lot of mistakes, they are a little bit naive and silly and they hallucinate a ton, a bit like children. It's kind of amusing. But what makes nanochat unique is that it is fully yours - fully configurable, tweakable, hackable, and trained by you from start to end. To train and talk to your own, we turn to...
+To get a sense of the endpoint of this repo, you can currently find [nanochat d32](https://github.com/karpathy/nanochat/discussions/8) hosted on [nanochat.karpathy.ai](https://nanochat.karpathy.ai/). "d32" means that this model has 32 layers in the Transformer neural network. This model has 1.9 billion parameters, it was trained on 38 billion tokens by simply running the single script [run1000.sh](run1000.sh), and the total cost of training was ~$800 (about 33 hours training time on 8XH100 GPU node). While today this is enough to outperform GPT-2 of 2019, it falls dramatically short of modern Large Language Models like GPT-5. When talking to these micro models, you'll see that they make a lot of mistakes, they are a little bit naive and silly and they hallucinate a ton, a bit like children. It's kind of amusing. But what makes nanochat unique is that it is fully yours - fully configurable, tweakable, hackable, and trained by you from start to end. To train and talk to your own, we turn to...
 
 ## Quick start
 
@@ -66,7 +66,7 @@ Total wall clock time: 3h51m
 
 ## Bigger models
 
-Unsurprisingly, $100 is not enough to train a highly performant ChatGPT clone. In fact, LLMs are famous for their multi-million dollar capex. For our purposes, I think there are two more scales of interest. First is the ~$300 tier d26 model (i.e. depth=26) that trains in ~12 hours, which slightly outperforms GPT-2 CORE score. Second is the $1000 tier (~41.6 hours), just because it's a nice round number. But both of these are not yet fully supported and therefore not attached here in the master branch yet.
+Unsurprisingly, $100 is not enough to train a highly performant ChatGPT clone. In fact, LLMs are famous for their multi-million dollar CapEx. For our purposes, I think there are two more scales of interest. First is the ~$300 tier d26 model (i.e. depth=26) that trains in ~12 hours, which slightly outperforms GPT-2 CORE score. Second is the $1000 tier (~41.6 hours), just because it's a nice round number. But both of these are not yet fully supported and therefore not attached here in the master branch yet.
 
 That said, to give a sense, the example changes needed for the [speedrun.sh](speedrun.sh) file to train a GPT-2 grade model d26 only involve three changes:
 
@@ -95,7 +95,7 @@ And a bit more about computing environments that will run nanochat:
 
 ## Running on CPU / MPS
 
-If you'd like to tinker with nanochat on your Macbook or a CPU machine, there is a work in progress [CPU|MPS PR](https://github.com/karpathy/nanochat/pull/88) up here. If you're on Macbook, use `--device_type=mps` when running `base_train.py`. See the PR and its diff for more. You're not going to get too far without GPU nodes, but at least you'll be able to run the code and maybe train a very tiny LLM with some patience.
+If you'd like to tinker with nanochat on your MacBook or a CPU machine, there is a work in progress [CPU|MPS PR](https://github.com/karpathy/nanochat/pull/88) up here. If you're on MacBook, use `--device_type=mps` when running `base_train.py`. See the PR and its diff for more. You're not going to get too far without GPU nodes, but at least you'll be able to run the code and maybe train a very tiny LLM with some patience.
 
 ## Questions
 
@@ -125,7 +125,7 @@ nanochat is nowhere finished. The goal is to improve the state of the art in mic
 
 - The name (nanochat) derives from my earlier project [nanoGPT](https://github.com/karpathy/nanoGPT), which only covered pretraining.
 - nanochat is also inspired by [modded-nanoGPT](https://github.com/KellerJordan/modded-nanogpt), which gamified the nanoGPT repo with clear metrics and a leaderboard, and borrows a lot of its ideas and some implementation for pretraining.
-- Thank you to [HuggingFace](https://huggingface.co/) for fineweb and smoltalk.
+- Thank you to [HuggingFace](https://huggingface.co/) for FineWeb and SmolTalk.
 - Thank you [Lambda](https://lambda.ai/service/gpu-cloud) for the compute used in developing this project.
 - Thank you to chief LLM whisperer 🧙‍♂️ Alec Radford for advice/guidance.