Updated to o200k_base

Underscore only sole space patches

Better handling of spaces

update default prompt

Updating description

Fixing proper UTF-8 representation

Updating to use new args file

Updating decription

local block causal when cuda avail

xformers when cuda available

Xformers pkg version update

Removing sphinx version spec

Adding spaces GPU decorator

Removing specified CUDA version

Changing HF Space python version

Adding HF ZeroGPU torch version compatible

Revert "Removing CUDA deps"

cleaning things up via gemini 2.5 pro

more finishing touches

adding patch counts and cleaning up

tiktoken & llama both plotted

Patches

Working locally, TBD HF space

Removing CUDA deps

Not sure what happened, more deps

Adding again

Removing gcc and gnu deps from req file

Init for HF space

Visualisation working on CPU via CUDA_VISIBLE_DEVICE=-1 python demo_patcher.py 'Daenerys Targaryen is in Game of Thrones, a fantasy epic by George R.R. Martin.'

Improve HF integration (#98)

Open source weights! (#97)

Cast int sample id to str (#96)

Init distributed when loading model (#94)

Fix eval mask (#93)

remove selective activation checkpointing (#92)

update (#91)

Get generation working for BLT (#86)

Fix in-place addition of patch_embds (#85)

Some fixes for entropy model predictions (#83)

Update ppl evals to work with blt model, in addition to entropy model (#82)

Update iterate_data (#81)

Add way to call consolidate (#80)

When merging configs, do not merge data sources (#79)

Get evals working again. (#46)

Reduce per file resources arrow uses (#77)

Let process start before yielding preloaded prefetch buffer, avoid needlessly losing buffer in edge cases (#75)

Add approximate state persistence (#73)

Fix rsync to not preserve original permissions, instead use destination (#76)

Correctly reset batch iterator at each arrow create_iter call. (#74)

Pass mask in packing_iterator, correctly handle last batch, fix masking (#65)