Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
Spaces:
Dovakiins
/
qwerrwe
like
0
Build error
App
Files
Files
Community
81da7d2
qwerrwe
/
src
/
axolotl
100 contributors
History:
707 commits
bofenghuang
Fix `total_num_steps` (#1566)
81da7d2
unverified
7 months ago
cli
feat: Add LLaMA-3 instruct prompt strategies for fine-tuning (#1553)
7 months ago
common
support for true batches with multipack (#1230)
10 months ago
core
FIX: max_length and max_prompt_length was not being sent to ORPOTrainer (#1584)
7 months ago
models
Phi2 multipack (#1173)
10 months ago
monkeypatch
adding llama3 fastchat conversation monkeypatch (#1539)
7 months ago
prompt_strategies
Llama3 dpo (#1610)
7 months ago
utils
Fix `total_num_steps` (#1566)
7 months ago
__init__.py
0 Bytes
WIP for axolotl trainer
over 1 year ago
convert.py
Safe
1.88 kB
Lint convert.py
over 1 year ago
datasets.py
Safe
7.44 kB
Pretrain transforms (#1261)
10 months ago
logging_config.py
Safe
1.92 kB
Don't disable existing loggers when configuring axolotl logging (#1395)
9 months ago
loraplus.py
Safe
4.67 kB
lora+ support (#1352)
9 months ago
prompt_tokenizers.py
Safe
16.9 kB
Feat: Add sharegpt multirole (#1137)
8 months ago
prompters.py
Safe
15.2 kB
feat: Add LLaMA-3 instruct prompt strategies for fine-tuning (#1553)
7 months ago
train.py
Safe
9.56 kB
make sure to save the lora adapter at the end of RL/dpo training (#1573)
7 months ago
