Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Spaces:
Dovakiins
/
qwerrwe
like
0
Build error
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
e923e62
qwerrwe
/
src
/
axolotl
Ctrl+K
Ctrl+K
100 contributors
History:
582 commits
winglian
more checks and fixes for deepspeed and fsdp (#1208) [skip ci]
e923e62
unverified
over 1 year ago
cli
make sure to register the base chatml template even if no system message is provided (#1207)
over 1 year ago
common
Create preprocess CLI (#785)
over 1 year ago
core
precompute dpo logprobs setting and fixes (#1199) [skip ci]
over 1 year ago
models
Phi2 multipack (#1173)
over 1 year ago
monkeypatch
Mixtral fixes 20240124 (#1192) [skip ci]
over 1 year ago
prompt_strategies
precompute dpo logprobs setting and fixes (#1199) [skip ci]
over 1 year ago
utils
more checks and fixes for deepspeed and fsdp (#1208) [skip ci]
over 1 year ago
__init__.py
Safe
0 Bytes
WIP for axolotl trainer
about 2 years ago
convert.py
Safe
1.88 kB
Lint convert.py
almost 2 years ago
datasets.py
7.45 kB
Add desc to map/filter (#1162)
over 1 year ago
logging_config.py
Safe
1.88 kB
log rank too (#527)
over 1 year ago
prompt_tokenizers.py
Safe
16 kB
fix: `train_on_inputs: true` ignored for sharegpt (#1045) [skip ci]
over 1 year ago
prompters.py
Safe
13.8 kB
Standardize system prompt format for AlpacaPrompter (#1190) [skip ci]
over 1 year ago
train.py
8.81 kB
workaround for transformers bug requireing do_sample for saveing pretrained (#1206)
over 1 year ago
