Commit History
Merge pull request #224 from OpenAccess-AI-Collective/system-prompt-data
f150c02
unverified
Merge pull request #244 from OpenAccess-AI-Collective/push-to-hub
5c39c00
unverified
push intermediate model checkpoints to hub
612aabd
Merge pull request #243 from OpenAccess-AI-Collective/unprompted-instruct
af05883
unverified
skip the system prompt
05ab909
pylint for duplicated code for system prompts
7b57ed7
add tests and supoort for loader for sys prompt data
3a38271
initial wip to get sys prompt from dataset
8d20e0a
Merge pull request #240 from OpenAccess-AI-Collective/tokenizer-fast
de8ed22
unverified
Merge pull request #241 from OpenAccess-AI-Collective/py3-pre-commit
478d8c7
unverified
better py3 support w pre-commit
645c135
optionally define whether to use_fast tokenizer
47d601f
Merge pull request #218 from OpenAccess-AI-Collective/no-fail-fast
756dfba
unverified
Merge pull request #235 from msinha251/Fixing-data-readme
91ab059
unverified
Fixing Data Readme
0aeb7c7
Mahesh Sinha
commited on
don't fail fast
d35278a
Merge pull request #215 from OpenAccess-AI-Collective/adamw-hyperparams-cfg
9492d4e
unverified
Additional test case per pr
ad5ca4f
add validation and tests for adamw hyperparam
cb9d3af
add docs
c969f0a
support adamw and grad norm hyperparams
6d0ee4b
Merge pull request #212 from OpenAccess-AI-Collective/doc-20230615-v1
a81f52d
unverified
Merge pull request #214 from OpenAccess-AI-Collective/fix-tokenizing-labels
1925eaf
unverified
fix test name
1ab3bf3
hint to what AMP means
d7635b7
add float16 docs and tweak typehints
88e17ff
ingore duplicate code in tests
baed440
bugfix for potential off by one
7925ddc
Merge pull request #206 from MaciejKarasek/issue205
6f84980
unverified
Merge pull request #209 from sroecker/fix_redpajama_example_tokenizer
c16644d
unverified
Use AutoTokenizer for redpajama example
945c419
style correction
136522f
maciej.karasek
commited on
issue #205 bugfix
556fe40
maciej.karasek
commited on
