show script 85b91e2
div18 commited on
Commit History
docs(blog): add comprehensive AntiAtropos project blog post cbb5245
div18 commited on
prompt fixes 8c4ef5c
div18 commited on
final commit aaad9f1
div18 commited on
prompt changes 8425a53
div18 commited on
prompts c157063
div18 commited on
fix CPU tensors e408dca
div18 commited on
fix bug 69f37e9
div18 commited on
reward etc tuning 67810ba
div18 commited on
fix logging 746de52
div18 commited on
cimmits c2815cb
div18 commited on
env changes 70cdeae
div18 commited on
training changes 7dbb622
div18 commited on
entropy spread d23c9c4
div18 commited on
better entropy c56d720
div18 commited on
grad messup d6b3052
div18 commited on
softer logits eae0446
div18 commited on
OOM 0f6141d
div18 commited on
OOM? a1a33c8
div18 commited on
LORA 8a3d2d7
div18 commited on
OOM 381091a
div18 commited on
don't OOM 86112b1
div18 commited on
Ms b1e6564
div18 commited on
mm 836c3a5
div18 commited on
OOM 863bb8c
div18 commited on
smaller logits 1b9be85
div18 commited on
Fix OOM d2f9b0c
div18 commited on
fixes d222529
div18 commited on
fixes 46cd5c4
div18 commited on
fix backprop 871c1ae
div18 commited on
changes d41d25d
div18 commited on
fix heuristic eb34c8c
div18 commited on
fix sft a891c04
div18 commited on
fix structure fa8da3f
div18 commited on
edits 619e74d
div18 commited on
fix: disable Qwen thinking at Jinja template level with enable_thinking=False 570dc24
div18 commited on
utils ba5f05d
div18 commited on
fix: disable Qwen thinking at Jinja template level with enable_thinking=False 5edb1ce
div18 commited on
fix: disable Qwen thinking at Jinja template level with enable_thinking=False 65788cc
div18 commited on
fix: add /no_think to system prompts, strip TRACE blocks from model output 9fd06fa
div18 commited on
fixes 75c8df1
div18 commited on
fix: install unsloth_zoo from git to match unsloth version 1701614
div18 commited on
changes 8a38e45
div18 commited on
fix: upgrade to pytorch 2.11.0 base image for torchao compatibility 051cd7f
div18 commited on
fix: remove torchao — incompatible with pytorch 2.6 base image 8c3b7f8
div18 commited on
fix: CUDA image, unsloth_zoo dep, total_memory, Docker-style job launch 182c625
div18 commited on
fix: CUDA image, unsloth_zoo dep, total_memory, Docker-style job launch f6430fd
div18 commited on
scrupt 69e18ac
div18 commited on
anti 4155294
div18 commited on
fix: CUDA image, unsloth_zoo dep, total_memory, Docker-style job launch 51f76e9
div18 commited on