mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-04 05:10:06 +06:00
96eb06286b
* current working example! * commit regex and result file * update * nit * push the conversion file * oups * roadmap and nits * attempt diffs for 3 files * persimmon * nit * add diff file that is the same as the modeling_llama.py * fix rope nits * updates * updates with converted versions * give some breathing space to the code * delete * update * update * push the actual result * update regex patterns * update regex patterns * fix some issues * fix some issues * fix some issues * updates * updates * updates * updates * updates * revert changes done to llama * updates * update gemma * updates * oups * current state * current state * update * ouiiii * nit * clear diffs * nit * fixup * update * doc 🚀 * 🔥 * for now use gemma * deal with comments * style * handle funtions * deal with assigns * todos * process inheritage * keep decorators? * 🤗 * deal with duplicates * fixup * correctly remove duplicate code * run ruff post script * ruff deals pretty well with imports, let's leave it to him * ah maybe not lol * for now remove all imports from child. * nit * conversion of llama * okay * convert starcoder2 * synch with main * update llama diff * updates * https://docs.astral.sh/ruff/rules/redefined-while-unused/ fixes the imports, bit needs later version of ruff * updates * okay actual state * non zero exit * update! * revert unrelated * remove other diff files * updates * cleanup * update * less diff! * stash * current updates * updates * No need for call * finished fining deps * update * current changes * current state * current state * new status * nit * finally * fixes * nits * order is now expected * use logger info instead of prints * fixup * up * nit * update * nits * update * correct merge * update * update * update * add warning * update caution message * update * better merging strategy * copy class statements :wink * fixups * nits * update * Apply suggestions from code review Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com> * nits * smaller header * do cleanup some stuff * even simpler header? * fixup * updates * ruff * update examples * nit * TODO * state * OUUUUUUF * current state * nits * final state * add a readme * fixup * remove diff llama * fix * nit * dummy noy funny * ruff format tests src utils --check * everless diffs * less diffs and fix test * fixes * naming nit? * update converter and add supper example * nits * updated for function signatures * update * update * add converted dummies * autoformat * single target assign fix * fixup * fix some imports * fixes * don't push them * `# noqa: F841` --------- Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
31 lines
829 B
Python
31 lines
829 B
Python
# Example where we only want to overwrite the defaults of an init
|
|
|
|
from transformers.models.gemma.configuration_gemma import GemmaConfig
|
|
|
|
|
|
class NewModelConfig(GemmaConfig):
|
|
def __init__(
|
|
self,
|
|
vocab_size=256030,
|
|
hidden_size=64,
|
|
intermediate_size=90,
|
|
num_hidden_layers=28,
|
|
num_attention_heads=16,
|
|
num_key_value_heads=16,
|
|
head_dim=256,
|
|
hidden_act="gelu_pytorch_tanh",
|
|
hidden_activation=None,
|
|
max_position_embeddings=1500,
|
|
initializer_range=0.02,
|
|
rms_norm_eps=1e-6,
|
|
use_cache=True,
|
|
pad_token_id=0,
|
|
eos_token_id=1,
|
|
bos_token_id=2,
|
|
tie_word_embeddings=True,
|
|
rope_theta=10000.0,
|
|
attention_bias=False,
|
|
attention_dropout=0.0,
|
|
):
|
|
super().__init__(self)
|