* Fix pad token * Update llama.py * Typo * ignored labels * Revert "ignored labels" This reverts commit4b25138ac7. * More patching * Update _utils.py * Update _utils.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Feat/all tmp (#1219) * Update save.py Check whether path is in /tmp dir for Kaggle environment * Update save.py Move temporary_location to /tmp in Kaggle * Enhance Kaggle environment support in save and tokenizer utilities --------- Co-authored-by: dendarrion <37800703+dendarrion@users.noreply.github.com> Co-authored-by: Erland366 <erland.pg366@gmail.com> * Bug fixes * Update pyproject.toml * Update _utils.py * Update __init__.py * Update __init__.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Tied weights * Revert "Tied weights" This reverts commit820cd4efef. * Tied weights * Utils * CE Loss patching * Update __init__.py * Update __init__.py * Patching * Update cross_entropy_loss.py * CE Loss * Update _utils.py * Update _utils.py * CE Loss * Update _utils.py * Update _utils.py * Layernorm * Update _utils.py * Update _utils.py * Post patch * Update _utils.py * Update llama.py * Update _utils.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * typing * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * int64 * Update _utils.py * Update cross_entropy_loss.py * constexpr * constexpr * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update _utils.py * Update _utils.py * Update _utils.py * CE * Update cross_entropy_loss.py * Update _utils.py * Update llama.py * Update _utils.py * Update rms_layernorm.py * Update rms_layernorm.py * Update rms_layernorm.py * Update rms_layernorm.py * Update rms_layernorm.py * Update rms_layernorm.py * Update utils.py * Update rms_layernorm.py * Update rms_layernorm.py * Update rms_layernorm.py * Update rms_layernorm.py * Update rms_layernorm.py * Update rms_layernorm.py * Update rms_layernorm.py * Update rms_layernorm.py * Update rms_layernorm.py * Update rms_layernorm.py * Update rms_layernorm.py * Update rms_layernorm.py * typing * Update rope_embedding.py * types * Disable compiling * Update _utils.py * Update _utils.py * Forward hook * Update _utils.py * Update llama.py * Update _utils.py * Update llama.py * Update llama.py * Update _utils.py * Update pyproject.toml * Update _utils.py * Update llama.py * CE Loss * Update cross_entropy_loss.py * Update _utils.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update cross_entropy_loss.py * Update llama.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Fix: cast logits to float32 in cross_entropy_forward to prevent errors (#1254) * Fix: cast logits to float32 in cross_entropy_forward to prevent errors * Update cross_entropy_loss.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Throw error when inferencing longer than max_popsition_embeddings (#1236) * Throw error when inferencing longer than max_popsition_embeddings without rope scaling * Update llama.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * CLI now handles user input strings for dtype correctly (#1235) Co-authored-by: root <root@ieeres.chu.cam.ac.uk> * Update flex_attention.py * Update _utils.py * Update _utils.py * Update flex_attention.py * Update flex_attention.py * Update loader.py * Update loader.py * Update flex_attention.py * Update flex_attention.py * Update flex_attention.py * Update flex_attention.py * Update _utils.py * Update cross_entropy_loss.py * Update _utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * triton_cast * Update utils.py * Qwen 2.5 Coder * Fix/export mistral (#1281) * Enhance install_python_non_blocking to handle protobuf installation and process management * Revert "Enhance install_python_non_blocking to handle protobuf installation and process management" This reverts commit a3b796a05841fb8d93c652c845591e12cf81ea93. * Set PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION to 'python' to address issue #1266 * Revert "Set PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION to 'python' to address issue #1266" This reverts commit f00fbf5eac7ad4f5d48c70b98d770255d1a9ef58. * Set PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION to 'python' to address issue #1266 * Update __init__.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * DOC Update - Update README.md with os.environ in example (#1269) * Update README.md with os.environ in example Added OS Environ in example to avoid device conflicts , for a user at least in jupyter notebook this allows to select GPU in a multi GPU setup. As currently the unsloth init checks all GPU's and takes the first in the order which can be a issue when some GPU's are in use and the list still shows them. So to manually avoid this, this os config is required. Small change but a bit time saver for those who straight away copies the tutorials * Update README.md --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * fix/get_chat_template (#1246) * Refactor `get_chat_template` to now support system message instead. It supposed to fix ollama tokenizer chattemplate to * Remove type hinting * Update chat_templates.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * fix/sft-trainer (#1276) * Add patch for SFTTrainer to maintain backward compatibility with TRL changes * Update trainer.py * Update trainer.py * Refactor trainer patch to maintain backward compatibility with TRL changes * Update trainer.py * Refactor trainer.py to exclude non-convertible trainers from backward compatibility patch --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update __init__.py * Update trainer.py * Update trainer.py * Update trainer.py * Update tokenizer_utils.py * Update llama.py * Fix #853 * fix/sfttrainer-compatibility (#1293) * Refactor trainer.py to import SFTConfig directly and update UnslothTrainingArguments class inheritance * Update trainer.py * Update trainer.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update rms_layernorm.py * Update rms_layernorm.py * Gemma * Update rms_layernorm.py * Update gemma2.py * Cut Cross Entropy * Update llama.py * Cut Cross Entropy * Update llama.py * Update llama.py * Update llama.py * Update __init__.py * Update __init__.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update mapper.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * patch_fast_lora * vision * Update fast_lora.py * Update _utils.py * Update _utils.py * Vision * Update trainer.py * Update save.py * FastBaseVisionModel * Update loader_utils.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update vision.py * Update _utils.py * tokenizer_name * Update loader.py * Update vision.py * Update save.py * Update save.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update _utils.py --------- Co-authored-by: dendarrion <37800703+dendarrion@users.noreply.github.com> Co-authored-by: Erland366 <erland.pg366@gmail.com> Co-authored-by: Edd <68678137+Erland366@users.noreply.github.com> Co-authored-by: Datta Nimmaturi <datta.nimmaturi@nutanix.com> Co-authored-by: Edwin Fennell <edwinfennell1@gmail.com> Co-authored-by: root <root@ieeres.chu.cam.ac.uk> Co-authored-by: Uday Girish Maradana <einsteingirish@gmail.com>
120 lines
5 KiB
Python
120 lines
5 KiB
Python
# Copyright 2023-present Daniel Han-Chen & the Unsloth team. All rights reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
from .mapper import INT_TO_FLOAT_MAPPER, FLOAT_TO_INT_MAPPER, MAP_TO_UNSLOTH_16bit
|
|
# https://github.com/huggingface/transformers/pull/26037 allows 4 bit loading!
|
|
from packaging.version import Version
|
|
from transformers import __version__ as transformers_version
|
|
transformers_version = Version(transformers_version)
|
|
SUPPORTS_FOURBIT = transformers_version >= Version("4.37")
|
|
|
|
|
|
def __get_model_name(
|
|
model_name,
|
|
load_in_4bit = True,
|
|
INT_TO_FLOAT_MAPPER = None,
|
|
FLOAT_TO_INT_MAPPER = None,
|
|
MAP_TO_UNSLOTH_16bit = None,
|
|
):
|
|
model_name = str(model_name)
|
|
lower_model_name = model_name.lower()
|
|
|
|
if not SUPPORTS_FOURBIT and lower_model_name in INT_TO_FLOAT_MAPPER:
|
|
|
|
model_name = INT_TO_FLOAT_MAPPER[lower_model_name]
|
|
print(
|
|
f"Unsloth: Your transformers version of {transformers_version} does not support native "\
|
|
f"4bit loading.\nThe minimum required version is 4.37.\n"\
|
|
f'Try `pip install --upgrade "transformers>=4.37"`\n'\
|
|
f"to obtain the latest transformers build, then restart this session.\n"\
|
|
f"For now, we shall load `{model_name}` instead (still 4bit, just slower downloading)."
|
|
)
|
|
return model_name
|
|
|
|
elif not load_in_4bit and lower_model_name in INT_TO_FLOAT_MAPPER:
|
|
|
|
new_model_name = INT_TO_FLOAT_MAPPER[lower_model_name]
|
|
# logger.warning_once(
|
|
# f"Unsloth: You passed in `{model_name}` which is a 4bit model, yet you set\n"\
|
|
# f"`load_in_4bit = False`. We shall load `{new_model_name}` instead."
|
|
# )
|
|
return new_model_name
|
|
|
|
elif not load_in_4bit and lower_model_name in MAP_TO_UNSLOTH_16bit:
|
|
|
|
new_model_name = MAP_TO_UNSLOTH_16bit[lower_model_name]
|
|
return new_model_name
|
|
|
|
elif load_in_4bit and SUPPORTS_FOURBIT and lower_model_name in FLOAT_TO_INT_MAPPER:
|
|
|
|
new_model_name = FLOAT_TO_INT_MAPPER[lower_model_name]
|
|
# logger.warning_once(
|
|
# f"Unsloth: You passed in `{model_name}` and `load_in_4bit = True`.\n"\
|
|
# f"We shall load `{new_model_name}` for 4x faster loading."
|
|
# )
|
|
return new_model_name
|
|
pass
|
|
|
|
return None
|
|
pass
|
|
|
|
|
|
def _get_new_mapper():
|
|
try:
|
|
import requests
|
|
new_mapper = "https://raw.githubusercontent.com/unslothai/unsloth/main/unsloth/models/mapper.py"
|
|
with requests.get(new_mapper, timeout = 3) as new_mapper: new_mapper = new_mapper.text
|
|
new_mapper = new_mapper[new_mapper.find("__INT_TO_FLOAT_MAPPER"):]
|
|
new_mapper = new_mapper\
|
|
.replace("INT_TO_FLOAT_MAPPER", "NEW_INT_TO_FLOAT_MAPPER")\
|
|
.replace("FLOAT_TO_INT_MAPPER", "NEW_FLOAT_TO_INT_MAPPER")\
|
|
.replace("MAP_TO_UNSLOTH_16bit", "NEW_MAP_TO_UNSLOTH_16bit")
|
|
|
|
exec(new_mapper, globals())
|
|
return NEW_INT_TO_FLOAT_MAPPER, NEW_FLOAT_TO_INT_MAPPER, NEW_MAP_TO_UNSLOTH_16bit
|
|
except:
|
|
return {}, {}, {}
|
|
pass
|
|
pass
|
|
|
|
|
|
def get_model_name(model_name, load_in_4bit = True):
|
|
new_model_name = __get_model_name(
|
|
model_name = model_name,
|
|
load_in_4bit = load_in_4bit,
|
|
INT_TO_FLOAT_MAPPER = INT_TO_FLOAT_MAPPER,
|
|
FLOAT_TO_INT_MAPPER = FLOAT_TO_INT_MAPPER,
|
|
MAP_TO_UNSLOTH_16bit = MAP_TO_UNSLOTH_16bit,
|
|
)
|
|
if new_model_name is None and model_name.count("/") == 1 and model_name[0].isalnum():
|
|
# Try checking if a new Unsloth version allows it!
|
|
NEW_INT_TO_FLOAT_MAPPER, NEW_FLOAT_TO_INT_MAPPER, NEW_MAP_TO_UNSLOTH_16bit = _get_new_mapper()
|
|
upgraded_model_name = __get_model_name(
|
|
model_name = model_name,
|
|
load_in_4bit = load_in_4bit,
|
|
INT_TO_FLOAT_MAPPER = NEW_INT_TO_FLOAT_MAPPER,
|
|
FLOAT_TO_INT_MAPPER = NEW_FLOAT_TO_INT_MAPPER,
|
|
MAP_TO_UNSLOTH_16bit = NEW_MAP_TO_UNSLOTH_16bit,
|
|
)
|
|
if upgraded_model_name is not None:
|
|
raise NotImplementedError(
|
|
f"Unsloth: {model_name} is not supported in your current Unsloth version! Please update Unsloth via:\n\n"\
|
|
'pip uninstall unsloth unsloth_zoo -y\n'\
|
|
'pip install --upgrade --no-cache-dir "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"\n'\
|
|
'pip install --upgrade --no-cache-dir "git+https://github.com/unslothai/unsloth-zoo.git"\n'\
|
|
)
|
|
pass
|
|
pass
|
|
return new_model_name if new_model_name is not None else model_name
|
|
pass
|