Abylay Ospan
ed63b87682
Make speedrun.sh configurable for different GPU setups
...
Added --nproc-per-node and --device-batch-size arguments so the script
can run on smaller hardware. Default is still 8 GPUs for the original
speedrun, but now you can do --nproc-per-node=1 --device-batch-size=2
for a single 16GB GPU.
2025-10-16 01:41:26 +00:00
Andrej Karpathy
4346536ab2
also allow regenerating assistant message by clicking it, and make sure to feed good seed to generate
2025-10-16 01:28:37 +00:00
Andrej Karpathy
2846999b8f
allow user to click on their message to edit them. conversation after that point is wiped
2025-10-16 01:16:22 +00:00
Andrej Karpathy
92d52ecc92
add slash commands to webui
2025-10-16 01:09:53 +00:00
Andrej Karpathy
fae3aca951
add script to train a 000 version of nanochat. currently it's a bit more like 00 and this would run in probably around 33 hours instead of the budget of 41 hours, so we might tune it later. i think it's ok for now
2025-10-15 20:32:22 +00:00
Andrej Karpathy
4c3590c499
fix subtle issue in token decoding in cases where multiple utf8 bytes need to be emitted into a single codepoint. exampels are emoji or foreign languages. basically we have to accumulate token sequences/text and only emit when we get full codepoints
2025-10-15 20:29:54 +00:00
Andrej Karpathy
03fa673b7d
add basic logging to chat_web, which i think might be fun
2025-10-15 19:51:06 +00:00
Andrej Karpathy
52bfeea8bd
add very basic abuse prevention limits to chat_web so it's ok to host endpoints
2025-10-15 19:42:54 +00:00
Andrej Karpathy
01fb290f53
allow multiple GPUs to do inference in a data parallel way
2025-10-15 19:12:19 +00:00
Andrej Karpathy
190d9515d0
dont evaluate the sampling evals during SFT they are too slow. keep the multiple choice evals. delete unused imports
2025-10-15 16:42:23 +00:00
Andrej Karpathy
b8076dd367
fix bug in learning rate multiplier, it was ramping up instead of ramping down. see more in Issue #68 . also add --dry_run option useful for experimentation
2025-10-15 16:35:04 +00:00
Andrej
67aaca98f5
export NANOCHAT_BASE_DIR so child processes get it too
...
Export the cache directory so that users can use their own cache location
2025-10-14 16:01:28 -07:00
Zach Mueller
f0855cbcc7
Update speedrun.sh
2025-10-14 14:12:01 -04:00
Andrej
dd6ff9a1cc
fix bug in fallback case of find_largest_model
...
Fix: Handle missing d<number> model tags in find_largest_model
ty
2025-10-13 14:38:34 -07:00
Mirza-Samad-Ahmed-Baig
afaa5b4c90
Fix: Handle missing d<number> model tags in find_largest_model
2025-10-14 00:24:07 +03:00
Andrej
5fd0b13886
Merge pull request #2 from epoyraz/patch-1
...
Update README.md
2025-10-13 10:10:15 -07:00
Enes Poyraz
6a795baf27
Update README.md
...
fix typos
2025-10-13 18:40:12 +02:00
Andrej
626bd3e260
Add image of the WebUI to readme
2025-10-13 08:03:00 -07:00
karpathy
da96b46565
update link to the new discussion
2025-10-13 07:42:09 -07:00
karpathy
a53833d04f
add nanochat logo png
2025-10-13 06:59:59 -07:00
karpathy
3a5e0bc50b
initial commit
2025-10-13 06:49:24 -07:00
