e2b23f17b1
* use exact model name
* Update save.py
* Update _utils.py
* Update _utils.py
* Update _utils.py
* Update _utils.py
* print
* Update _utils.py
* Update _utils.py
* Update llama.py
* Update _utils.py
* Update vision.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 loader.py
* accurate_accumulation
* Update loader.py
* Update loader.py
* Update _utils.py
* Update loader.py
* Update loader.py
* Update loader.py
* Update loader.py
* Update pyproject.toml
* Update __init__.py
* Update pyproject.toml
* Update __init__.py
* Update __init__.py
* Fix Triton heuristics
https://github.com/triton-lang/triton/issues/5224
* Update __init__.py
* Update __init__.py
* Update __init__.py
* Update __init__.py
* Xformers
* Update loader.py
* Update loader.py
* Rewind
* Update _utils.py
* Update _utils.py
* requires grad
* Update loader.py
* Update _utils.py
* Update loader.py
* changing model to base_model if peft model is already used
* Improve debugging experience (#1512)
* Create CONTRIBUTING.md (#1472)
Creating contributing guidelines
* Update CONTRIBUTING.md
improved sentence
* Improve logging control in `unsloth_compile_transformers` by conditionally redirecting stdout based on UNSLOTH_DISABLE_LOGGER environment variable
---------
Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com>
Co-authored-by: Nino Risteski <95188570+NinoRisteski@users.noreply.github.com>
* Update loader.py
* Update llama.py
* Update llama.py
* Revert "Update llama.py"
This reverts commit a8edd0931a.
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Auto change is_bfloat16_supported
* Update llama.py
* Force data-type
* Update llama.py
* All attention refactor fix (#1491)
* change initilization of n_heads, n_kv_heads, hidden_size in llama.py
* do the same for cohere, mistral, gemma2, granite
* do the same for flexattention,cohere, mistral, granite
* Update llama.py
* Update llama.py
* Update granite to work with latest post_patch methods (#1502)
* Update granite to work with latest post_patch methods
* Pass position_embeddings for granite even if transformers<4.47
* Update llama.py
---------
Co-authored-by: Daniel Han <danielhanchen@gmail.com>
* Minor fixes for granite models (#1503)
* Update granite.py
Grab residual multiplier directly from layer
* Update llama.py
Version should read >= 4.47.1 as that is the version requiring the changes
* Update granite.py
* Update llama.py
---------
Co-authored-by: Daniel Han <danielhanchen@gmail.com>
* support modelscope models and datasets (#1481)
* support modelscope
* change modelscope args
* remove useless import
* remove useless import
* fix
* wip
* fix
* remove useless code
* add readme
* add some comments
* change print to raise error
* update comment
* Update loader.py
---------
Co-authored-by: Daniel Han <danielhanchen@gmail.com>
* Merge branch 'main' into nightly
* Phi 4
* Update llama.py
* Torch.Cuda Is Available Condition and Warning (#1545)
* check for torch.cuda and triton if available
on my machine(mac m3) the cuda were not available
* Update pyproject.toml
* Update __init__.py
---------
Co-authored-by: Daniel Han <danielhanchen@gmail.com>
* Update mistral.py
* Update mistral.py
* Update _utils.py
* Update _utils.py
* Update _utils.py
* Update _utils.py
* Update _utils.py
* Fix
* Bug fixes
* Update mapper.py
* Add dropout to granite to match HF's implementation (#1557)
Signed-off-by: datta0 <venkatadattasainimmaturi@gmail.com>
* Update llama.py
* Update llama.py
* Bug fixes
* fix: flash_attn_detection_error (#1556)
* fix: flash_attn_detection_error
* Update _utils.py
---------
Co-authored-by: Daniel Han <danielhanchen@gmail.com>
* Update mapper.py
---------
Signed-off-by: datta0 <venkatadattasainimmaturi@gmail.com>
Co-authored-by: Itsuro Tajima <tajima@georepublic.de>
Co-authored-by: Muhammad Osama <muhammadosama1994@gmail.com>
Co-authored-by: Edd <68678137+Erland366@users.noreply.github.com>
Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com>
Co-authored-by: Nino Risteski <95188570+NinoRisteski@users.noreply.github.com>
Co-authored-by: Kareem <81531392+KareemMusleh@users.noreply.github.com>
Co-authored-by: Datta Nimmaturi <datta.nimmaturi@nutanix.com>
Co-authored-by: Z <coffeevampirebusiness@gmail.com>
Co-authored-by: tastelikefeet <58414341+tastelikefeet@users.noreply.github.com>
Co-authored-by: AminWhat <88392440+aminwhat@users.noreply.github.com>
Co-authored-by: Zhe Zhang <2631992879@qq.com>
618 lines
20 KiB
Python
618 lines
20 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.
|
|
|
|
__all__ = [
|
|
"INT_TO_FLOAT_MAPPER",
|
|
"FLOAT_TO_INT_MAPPER",
|
|
]
|
|
|
|
__INT_TO_FLOAT_MAPPER = \
|
|
{
|
|
"unsloth/mistral-7b-bnb-4bit" : (
|
|
"unsloth/mistral-7b",
|
|
"mistralai/Mistral-7B-v0.1",
|
|
),
|
|
"unsloth/llama-2-7b-bnb-4bit" : (
|
|
"unsloth/llama-2-7b",
|
|
"meta-llama/Llama-2-7b-hf",
|
|
),
|
|
"unsloth/llama-2-13b-bnb-4bit" : (
|
|
"unsloth/llama-2-13b",
|
|
"meta-llama/Llama-2-13b-hf",
|
|
),
|
|
"unsloth/codellama-34b-bnb-4bit" : (
|
|
"codellama/CodeLlama-34b-hf",
|
|
),
|
|
"unsloth/zephyr-sft-bnb-4bit" : (
|
|
"unsloth/zephyr-sft",
|
|
"HuggingFaceH4/mistral-7b-sft-beta",
|
|
),
|
|
"unsloth/tinyllama-bnb-4bit" : (
|
|
"unsloth/tinyllama",
|
|
"TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
|
|
),
|
|
"unsloth/tinyllama-chat-bnb-4bit" : (
|
|
"unsloth/tinyllama-chat",
|
|
"TinyLlama/TinyLlama-1.1B-Chat-v1.0",
|
|
),
|
|
"unsloth/mistral-7b-instruct-v0.1-bnb-4bit" : (
|
|
"unsloth/mistral-7b-instruct-v0.1",
|
|
"mistralai/Mistral-7B-Instruct-v0.1",
|
|
),
|
|
"unsloth/mistral-7b-instruct-v0.2-bnb-4bit" : (
|
|
"unsloth/mistral-7b-instruct-v0.2",
|
|
"mistralai/Mistral-7B-Instruct-v0.2",
|
|
),
|
|
"unsloth/llama-2-7b-chat-bnb-4bit" : (
|
|
"unsloth/llama-2-7b-chat",
|
|
"meta-llama/Llama-2-7b-chat-hf",
|
|
),
|
|
"unsloth/llama-2-7b-chat-bnb-4bit" : (
|
|
"unsloth/llama-2-7b-chat",
|
|
"meta-llama/Llama-2-7b-chat-hf",
|
|
),
|
|
"unsloth/codellama-7b-bnb-4bit" : (
|
|
"unsloth/codellama-7b",
|
|
"codellama/CodeLlama-7b-hf",
|
|
),
|
|
"unsloth/codellama-13b-bnb-4bit" : (
|
|
"codellama/CodeLlama-13b-hf",
|
|
),
|
|
"unsloth/yi-6b-bnb-4bit" : (
|
|
"unsloth/yi-6b",
|
|
"01-ai/Yi-6B",
|
|
),
|
|
"unsloth/solar-10.7b-bnb-4bit" : (
|
|
"upstage/SOLAR-10.7B-v1.0",
|
|
),
|
|
"unsloth/gemma-7b-bnb-4bit" : (
|
|
"unsloth/gemma-7b",
|
|
"google/gemma-7b",
|
|
),
|
|
"unsloth/gemma-2b-bnb-4bit" : (
|
|
"unsloth/gemma-2b",
|
|
"google/gemma-2b",
|
|
),
|
|
"unsloth/gemma-7b-it-bnb-4bit" : (
|
|
"unsloth/gemma-7b-it",
|
|
"google/gemma-7b-it",
|
|
),
|
|
"unsloth/gemma-2b-bnb-4bit" : (
|
|
"unsloth/gemma-2b-it",
|
|
"google/gemma-2b-it",
|
|
),
|
|
"unsloth/mistral-7b-v0.2-bnb-4bit" : (
|
|
"unsloth/mistral-7b-v0.2",
|
|
"alpindale/Mistral-7B-v0.2-hf",
|
|
),
|
|
"unsloth/gemma-1.1-2b-it-bnb-4bit" : (
|
|
"unsloth/gemma-1.1-2b-it",
|
|
"google/gemma-1.1-2b-it",
|
|
),
|
|
"unsloth/gemma-1.1-7b-it-bnb-4bit" : (
|
|
"unsloth/gemma-1.1-7b-it",
|
|
"google/gemma-1.1-7b-it",
|
|
),
|
|
"unsloth/Starling-LM-7B-beta-bnb-4bit" : (
|
|
"unsloth/Starling-LM-7B-beta",
|
|
"Nexusflow/Starling-LM-7B-beta",
|
|
),
|
|
"unsloth/Hermes-2-Pro-Mistral-7B-bnb-4bit" : (
|
|
"unsloth/Hermes-2-Pro-Mistral-7B",
|
|
"NousResearch/Hermes-2-Pro-Mistral-7B",
|
|
),
|
|
"unsloth/OpenHermes-2.5-Mistral-7B-bnb-4bit" : (
|
|
"unsloth/OpenHermes-2.5-Mistral-7B",
|
|
"teknium/OpenHermes-2.5-Mistral-7B",
|
|
),
|
|
"unsloth/codegemma-2b-bnb-4bit" : (
|
|
"unsloth/codegemma-2b",
|
|
"google/codegemma-2b",
|
|
),
|
|
"unsloth/codegemma-7b-bnb-4bit" : (
|
|
"unsloth/codegemma-7b",
|
|
"google/codegemma-7b",
|
|
),
|
|
"unsloth/codegemma-7b-it-bnb-4bit" : (
|
|
"unsloth/codegemma-7b-it",
|
|
"google/codegemma-7b-it",
|
|
),
|
|
"unsloth/llama-3-8b-bnb-4bit" : (
|
|
"unsloth/llama-3-8b",
|
|
"meta-llama/Meta-Llama-3-8B",
|
|
),
|
|
"unsloth/llama-3-8b-Instruct-bnb-4bit" : (
|
|
"unsloth/llama-3-8b-Instruct",
|
|
"meta-llama/Meta-Llama-3-8B-Instruct",
|
|
),
|
|
"unsloth/llama-3-70b-bnb-4bit" : (
|
|
"meta-llama/Meta-Llama-3-70B",
|
|
),
|
|
"unsloth/llama-3-70b-Instruct-bnb-4bit" : (
|
|
"meta-llama/Meta-Llama-3-70B-Instruct",
|
|
),
|
|
"unsloth/Phi-3-mini-4k-instruct-bnb-4bit" : (
|
|
"unsloth/Phi-3-mini-4k-instruct",
|
|
"microsoft/Phi-3-mini-4k-instruct",
|
|
),
|
|
"unsloth/mistral-7b-v0.3-bnb-4bit" : (
|
|
"unsloth/mistral-7b-v0.3",
|
|
"mistralai/Mistral-7B-v0.3",
|
|
),
|
|
"unsloth/mistral-7b-instruct-v0.3-bnb-4bit" : (
|
|
"unsloth/mistral-7b-instruct-v0.3",
|
|
"mistralai/Mistral-7B-Instruct-v0.3",
|
|
),
|
|
"unsloth/Phi-3-medium-4k-instruct-bnb-4bit" : (
|
|
"unsloth/Phi-3-medium-4k-instruct",
|
|
"microsoft/Phi-3-medium-4k-instruct",
|
|
),
|
|
"unsloth/Qwen2-0.5B-bnb-4bit" : (
|
|
"unsloth/Qwen2-0.5B",
|
|
"Qwen/Qwen2-0.5B",
|
|
),
|
|
"unsloth/Qwen2-0.5B-Instruct-bnb-4bit" : (
|
|
"unsloth/Qwen2-0.5B-Instruct",
|
|
"Qwen/Qwen2-0.5B-Instruct",
|
|
),
|
|
"unsloth/Qwen2-1.5B-bnb-4bit" : (
|
|
"unsloth/Qwen2-1.5B",
|
|
"Qwen/Qwen2-1.5B",
|
|
),
|
|
"unsloth/Qwen2-1.5B-Instruct-bnb-4bit" : (
|
|
"unsloth/Qwen2-1.5B-Instruct",
|
|
"Qwen/Qwen2-1.5B-Instruct",
|
|
),
|
|
"unsloth/Qwen2-7B-bnb-4bit" : (
|
|
"unsloth/Qwen2-7B",
|
|
"Qwen/Qwen2-7B",
|
|
),
|
|
"unsloth/Qwen2-7B-Instruct-bnb-4bit" : (
|
|
"unsloth/Qwen2-7B-Instruct",
|
|
"Qwen/Qwen2-7B-Instruct",
|
|
),
|
|
"unsloth/Qwen2-70B-bnb-4bit" : (
|
|
"Qwen/Qwen2-70B",
|
|
),
|
|
"unsloth/Qwen2-70B-Instruct-bnb-4bit" : (
|
|
"Qwen/Qwen2-70B-Instruct",
|
|
),
|
|
"mistralai/Codestral-22B-v0.1" : (
|
|
"mistral-community/Codestral-22B-v0.1",
|
|
),
|
|
"unsloth/gemma-2-9b-bnb-4bit" : (
|
|
"unsloth/gemma-2-9b",
|
|
"google/gemma-2-9b",
|
|
),
|
|
"unsloth/gemma-2-27b-bnb-4bit" : (
|
|
"unsloth/gemma-2-27b",
|
|
"google/gemma-2-27b",
|
|
),
|
|
"unsloth/gemma-2-9b-it-bnb-4bit" : (
|
|
"unsloth/gemma-2-9b-it",
|
|
"google/gemma-2-9b-it",
|
|
),
|
|
"unsloth/gemma-2-27b-it-bnb-4bit" : (
|
|
"unsloth/gemma-2-27b-it",
|
|
"google/gemma-2-27b-it",
|
|
),
|
|
"unsloth/Phi-3-mini-4k-instruct-v0-bnb-4bit" : ( # Old Phi pre July
|
|
"unsloth/Phi-3-mini-4k-instruct-v0",
|
|
),
|
|
"unsloth/Mistral-Nemo-Instruct-2407-bnb-4bit" : ( # New 12b Mistral models
|
|
"unsloth/Mistral-Nemo-Instruct-2407",
|
|
"mistralai/Mistral-Nemo-Instruct-2407",
|
|
),
|
|
"unsloth/Mistral-Nemo-Base-2407-bnb-4bit" : ( # New 12b Mistral models
|
|
"unsloth/Mistral-Nemo-Base-2407",
|
|
"mistralai/Mistral-Nemo-Base-2407",
|
|
),
|
|
"unsloth/Meta-Llama-3.1-8B-bnb-4bit" : (
|
|
"unsloth/Meta-Llama-3.1-8B",
|
|
"meta-llama/Meta-Llama-3.1-8B",
|
|
),
|
|
"unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit" : (
|
|
"unsloth/Meta-Llama-3.1-8B-Instruct",
|
|
"meta-llama/Meta-Llama-3.1-8B-Instruct",
|
|
),
|
|
"unsloth/Meta-Llama-3.1-70B-bnb-4bit" : (
|
|
"unsloth/Meta-Llama-3.1-70B",
|
|
"meta-llama/Meta-Llama-3.1-70B",
|
|
),
|
|
"unsloth/Meta-Llama-3.1-405B-bnb-4bit" : (
|
|
"meta-llama/Meta-Llama-3.1-405B",
|
|
),
|
|
"unsloth/Meta-Llama-3.1-405B-Instruct-bnb-4bit" : (
|
|
"meta-llama/Meta-Llama-3.1-405B-Instruct",
|
|
),
|
|
"unsloth/Meta-Llama-3.1-70B-Instruct-bnb-4bit" : (
|
|
"unsloth/Meta-Llama-3.1-70B-Instruct",
|
|
"meta-llama/Meta-Llama-3.1-70B-Instruct",
|
|
),
|
|
"unsloth/Mistral-Large-Instruct-2407-bnb-4bit" : (
|
|
"mistralai/Mistral-Large-Instruct-2407",
|
|
),
|
|
"unsloth/gemma-2-2b-bnb-4bit" : (
|
|
"unsloth/gemma-2-2b",
|
|
"google/gemma-2-2b",
|
|
),
|
|
"unsloth/gemma-2-2b-it-bnb-4bit" : (
|
|
"unsloth/gemma-2-2b-it",
|
|
"google/gemma-2-2b-it",
|
|
),
|
|
"unsloth/Phi-3.5-mini-instruct-bnb-4bit" : (
|
|
"unsloth/Phi-3.5-mini-instruct",
|
|
"microsoft/Phi-3.5-mini-instruct",
|
|
),
|
|
"unsloth/c4ai-command-r-08-2024-bnb-4bit" : (
|
|
"CohereForAI/c4ai-command-r-08-2024",
|
|
),
|
|
"unsloth/c4ai-command-r-plus-08-2024-bnb-4bit" : (
|
|
"CohereForAI/c4ai-command-r-plus-08-2024",
|
|
),
|
|
"unsloth/Llama-3.1-Storm-8B-bnb-4bit" : (
|
|
"unsloth/Llama-3.1-Storm-8B",
|
|
"akjindal53244/Llama-3.1-Storm-8B",
|
|
),
|
|
"unsloth/Hermes-3-Llama-3.1-8B-bnb-4bit" : (
|
|
"unsloth/Hermes-3-Llama-3.1-8B",
|
|
"NousResearch/Hermes-3-Llama-3.1-8B",
|
|
),
|
|
"unsloth/Hermes-3-Llama-3.1-70B-bnb-4bit" : (
|
|
"unsloth/Hermes-3-Llama-3.1-70B",
|
|
"NousResearch/Hermes-3-Llama-3.1-70B",
|
|
),
|
|
"unsloth/Hermes-3-Llama-3.1-405B-bnb-4bit" : (
|
|
"NousResearch/Hermes-3-Llama-3.1-405B",
|
|
),
|
|
"unsloth/SmolLM-135M-bnb-4bit" : (
|
|
"unsloth/SmolLM-135M",
|
|
"HuggingFaceTB/SmolLM-135M",
|
|
),
|
|
"unsloth/SmolLM-360M-bnb-4bit" : (
|
|
"unsloth/SmolLM-360M",
|
|
"HuggingFaceTB/SmolLM-360M",
|
|
),
|
|
"unsloth/SmolLM-1.7B-bnb-4bit" : (
|
|
"unsloth/SmolLM-1.7B",
|
|
"HuggingFaceTB/SmolLM-1.7B",
|
|
),
|
|
"unsloth/SmolLM-135M-Instruct-bnb-4bit" : (
|
|
"unsloth/SmolLM-135M-Instruct",
|
|
"HuggingFaceTB/SmolLM-135M-Instruct",
|
|
),
|
|
"unsloth/SmolLM-360M-Instruct-bnb-4bit" : (
|
|
"unsloth/SmolLM-360M-Instruct",
|
|
"HuggingFaceTB/SmolLM-360M-Instruct",
|
|
),
|
|
"unsloth/SmolLM-1.7B-Instruct-bnb-4bit" : (
|
|
"unsloth/SmolLM-1.7B-Instruct",
|
|
"HuggingFaceTB/SmolLM-1.7B-Instruct",
|
|
),
|
|
"unsloth/Mistral-Small-Instruct-2409-bnb-4bit" : (
|
|
"unsloth/Mistral-Small-Instruct-2409",
|
|
"mistralai/Mistral-Small-Instruct-2409",
|
|
),
|
|
"unsloth/Qwen2.5-0.5B-Instruct-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-0.5B-Instruct",
|
|
"Qwen/Qwen2.5-0.5B-Instruct",
|
|
),
|
|
"unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-1.5B-Instruct",
|
|
"Qwen/Qwen2.5-1.5B-Instruct",
|
|
),
|
|
"unsloth/Qwen2.5-3B-Instruct-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-3B-Instruct",
|
|
"Qwen/Qwen2.5-3B-Instruct",
|
|
),
|
|
"unsloth/Qwen2.5-7B-Instruct-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-7B-Instruct",
|
|
"Qwen/Qwen2.5-7B-Instruct",
|
|
),
|
|
"unsloth/Qwen2.5-14B-Instruct-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-14B-Instruct",
|
|
"Qwen/Qwen2.5-14B-Instruct",
|
|
),
|
|
"unsloth/Qwen2.5-32B-Instruct-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-32B-Instruct",
|
|
"Qwen/Qwen2.5-32B-Instruct",
|
|
),
|
|
"unsloth/Qwen2.5-72B-Instruct-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-72B-Instruct",
|
|
"Qwen/Qwen2.5-72B-Instruct",
|
|
),
|
|
"unsloth/Qwen2.5-0.5B-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-0.5B",
|
|
"Qwen/Qwen2.5-0.5B",
|
|
),
|
|
"unsloth/Qwen2.5-1.5B-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-1.5B",
|
|
"Qwen/Qwen2.5-1.5B",
|
|
),
|
|
"unsloth/Qwen2.5-3B-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-3B",
|
|
"Qwen/Qwen2.5-3B",
|
|
),
|
|
"unsloth/Qwen2.5-7B-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-7B",
|
|
"Qwen/Qwen2.5-7B",
|
|
),
|
|
"unsloth/Qwen2.5-14B-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-14B",
|
|
"Qwen/Qwen2.5-14B",
|
|
),
|
|
"unsloth/Qwen2.5-32B-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-32B",
|
|
"Qwen/Qwen2.5-32B",
|
|
),
|
|
"unsloth/Qwen2.5-72B-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-72B",
|
|
"Qwen/Qwen2.5-72B",
|
|
),
|
|
"unsloth/Qwen2.5-Math-1.5B-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-Math-1.5B",
|
|
"Qwen/Qwen2.5-Math-1.5B",
|
|
),
|
|
"unsloth/Qwen2.5-Math-7B-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-Math-7B",
|
|
"Qwen/Qwen2.5-Math-7B",
|
|
),
|
|
"unsloth/Qwen2.5-Math-72B-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-Math-72B",
|
|
"Qwen/Qwen2.5-Math-72B",
|
|
),
|
|
"unsloth/Qwen2.5-Math-1.5B-Instruct-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-Math-1.5B-Instruct",
|
|
"Qwen/Qwen2.5-Math-1.5B-Instruct",
|
|
),
|
|
"unsloth/Qwen2.5-Math-7B-Instruct-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-Math-7B-Instruct",
|
|
"Qwen/Qwen2.5-Math-7B-Instruct",
|
|
),
|
|
"unsloth/Qwen2.5-Math-72B-Instruct-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-Math-72B-Instruct",
|
|
"Qwen/Qwen2.5-Math-72B-Instruct",
|
|
),
|
|
"unsloth/Qwen2.5-Coder-0.5B-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-Coder-0.5B",
|
|
"Qwen/Qwen2.5-Coder-0.5B",
|
|
),
|
|
"unsloth/Qwen2.5-Coder-1.5B-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-Coder-1.5B",
|
|
"Qwen/Qwen2.5-Coder-1.5B",
|
|
),
|
|
"unsloth/Qwen2.5-Coder-3B-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-Coder-3B",
|
|
"Qwen/Qwen2.5-Coder-3B",
|
|
),
|
|
"unsloth/Qwen2.5-Coder-7B-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-Coder-7B",
|
|
"Qwen/Qwen2.5-Coder-7B",
|
|
),
|
|
"unsloth/Qwen2.5-Coder-14B-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-Coder-14B",
|
|
"Qwen/Qwen2.5-Coder-14B",
|
|
),
|
|
"unsloth/Qwen2.5-Coder-32B-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-Coder-32B",
|
|
"Qwen/Qwen2.5-Coder-32B",
|
|
),
|
|
"unsloth/Qwen2.5-Coder-0.5B-Instruct-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-Coder-0.5B-Instruct",
|
|
"Qwen/Qwen2.5-Coder-0.5B-Instruct",
|
|
),
|
|
"unsloth/Qwen2.5-Coder-1.5B-Instruct-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-Coder-1.5B-Instruct",
|
|
"Qwen/Qwen2.5-Coder-1.5B-Instruct",
|
|
),
|
|
"unsloth/Qwen2.5-Coder-3B-Instruct-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-Coder-3B-Instruct",
|
|
"Qwen/Qwen2.5-Coder-3B-Instruct",
|
|
),
|
|
"unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-Coder-7B-Instruct",
|
|
"Qwen/Qwen2.5-Coder-7B-Instruct",
|
|
),
|
|
"unsloth/Qwen2.5-Coder-14B-Instruct-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-Coder-14B-Instruct",
|
|
"Qwen/Qwen2.5-Coder-14B-Instruct",
|
|
),
|
|
"unsloth/Qwen2.5-Coder-32B-Instruct-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-Coder-32B-Instruct",
|
|
"Qwen/Qwen2.5-Coder-32B-Instruct",
|
|
),
|
|
"unsloth/Llama-3.2-1B-unsloth-bnb-4bit" : (
|
|
"unsloth/Llama-3.2-1B",
|
|
"meta-llama/Llama-3.2-1B",
|
|
"unsloth/Llama-3.2-1B-bnb-4bit",
|
|
),
|
|
"unsloth/Llama-3.2-3B-unsloth-bnb-4bit" : (
|
|
"unsloth/Llama-3.2-3B",
|
|
"meta-llama/Llama-3.2-3B",
|
|
"unsloth/Llama-3.2-3B-bnb-4bit",
|
|
),
|
|
"unsloth/Llama-3.2-1B-Instruct-unsloth-bnb-4bit" : (
|
|
"unsloth/Llama-3.2-1B-Instruct",
|
|
"meta-llama/Llama-3.2-1B-Instruct",
|
|
"unsloth/Llama-3.2-1B-Instruct-bnb-4bit",
|
|
),
|
|
"unsloth/Llama-3.2-3B-Instruct-unsloth-bnb-4bit" : (
|
|
"unsloth/Llama-3.2-3B-Instruct",
|
|
"meta-llama/Llama-3.2-3B-Instruct",
|
|
"unsloth/Llama-3.2-3B-Instruct-bnb-4bit",
|
|
),
|
|
"unsloth/Llama-3.1-Nemotron-70B-Instruct-bnb-4bit" : (
|
|
"unsloth/Llama-3.1-Nemotron-70B-Instruct",
|
|
"nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
|
|
),
|
|
"unsloth/Qwen2-VL-2B-Instruct-unsloth-bnb-4bit" : (
|
|
"unsloth/Qwen2-VL-2B-Instruct",
|
|
"Qwen/Qwen2-VL-2B-Instruct",
|
|
"unsloth/Qwen2-VL-2B-Instruct-bnb-4bit",
|
|
),
|
|
"unsloth/Qwen2-VL-7B-Instruct-unsloth-bnb-4bit" : (
|
|
"unsloth/Qwen2-VL-7B-Instruct",
|
|
"Qwen/Qwen2-VL-7B-Instruct",
|
|
"unsloth/Qwen2-VL-7B-Instruct-bnb-4bit",
|
|
),
|
|
"unsloth/Qwen2-VL-72B-Instruct-bnb-4bit" : (
|
|
"unsloth/Qwen2-VL-72B-Instruct",
|
|
"Qwen/Qwen2-VL-72B-Instruct",
|
|
),
|
|
"unsloth/Llama-3.2-11B-Vision-Instruct-unsloth-bnb-4bit" : (
|
|
"unsloth/Llama-3.2-11B-Vision-Instruct",
|
|
"meta-llama/Llama-3.2-11B-Vision-Instruct",
|
|
"unsloth/Llama-3.2-11B-Vision-Instruct-bnb-4bit",
|
|
),
|
|
"unsloth/Llama-3.2-90B-Vision-Instruct-bnb-4bit" : (
|
|
"unsloth/Llama-3.2-90B-Vision-Instruct",
|
|
"meta-llama/Llama-3.2-90B-Vision-Instruct",
|
|
),
|
|
"unsloth/Llama-3.2-11B-Vision-unsloth-bnb-4bit" : (
|
|
"unsloth/Llama-3.2-11B-Vision",
|
|
"meta-llama/Llama-3.2-11B-Vision",
|
|
"unsloth/Llama-3.2-11B-Vision-bnb-4bit",
|
|
),
|
|
"unsloth/Llama-3.2-90B-Vision-bnb-4bit" : (
|
|
"unsloth/Llama-3.2-90B-Vision",
|
|
"meta-llama/Llama-3.2-90B-Vision",
|
|
),
|
|
"unsloth/Pixtral-12B-2409-unsloth-bnb-4bit" : (
|
|
"unsloth/Pixtral-12B-2409",
|
|
"mistralai/Pixtral-12B-2409",
|
|
"unsloth/Pixtral-12B-2409-bnb-4bit",
|
|
),
|
|
"unsloth/Pixtral-12B-2409-Base-bnb-4bit" : (
|
|
"unsloth/Pixtral-12B-Base-2409",
|
|
"mistralai/Pixtral-12B-Base-2409",
|
|
),
|
|
"unsloth/llava-1.5-7b-hf-bnb-4bit" : (
|
|
"unsloth/llava-1.5-7b-hf",
|
|
"llava-hf/llava-1.5-7b-hf",
|
|
),
|
|
"unsloth/llava-v1.6-mistral-7b-hf-bnb-4bit" : (
|
|
"unsloth/llava-v1.6-mistral-7b-hf",
|
|
"llava-hf/llava-v1.6-mistral-7b-hf",
|
|
),
|
|
"unsloth/Llama-3.1-Tulu-3-8B-bnb-4bit" : (
|
|
"unsloth/Llama-3.1-Tulu-3-8B",
|
|
"allenai/Llama-3.1-Tulu-3-8B",
|
|
),
|
|
"unsloth/Llama-3.1-Tulu-3-70B-bnb-4bit" : (
|
|
"unsloth/Llama-3.1-Tulu-3-70B",
|
|
"allenai/Llama-3.1-Tulu-3-70B",
|
|
),
|
|
"unsloth/QwQ-32B-Preview-bnb-4bit" : (
|
|
"unsloth/QwQ-32B-Preview",
|
|
"Qwen/QwQ-32B-Preview",
|
|
),
|
|
"unsloth/Llama-3.3-70B-Instruct-bnb-4bit" : (
|
|
"unsloth/Llama-3.3-70B-Instruct",
|
|
"meta-llama/Llama-3.3-70B-Instruct",
|
|
),
|
|
"unsloth/phi-4-unsloth-bnb-4bit" : (
|
|
"unsloth/phi-4",
|
|
"microsoft/phi-4",
|
|
"unsloth/phi-4-bnb-4bit",
|
|
),
|
|
"unsloth/DeepSeek-R1-Distill-Qwen-32B-bnb-4bit" : (
|
|
"unsloth/DeepSeek-R1-Distill-Qwen-32B",
|
|
"deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
|
|
),
|
|
"unsloth/DeepSeek-R1-Distill-Qwen-14B-unsloth-bnb-4bit" : (
|
|
"unsloth/DeepSeek-R1-Distill-Qwen-14B",
|
|
"deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
|
|
"unsloth/DeepSeek-R1-Distill-Qwen-14B-bnb-4bit",
|
|
),
|
|
"unsloth/DeepSeek-R1-Distill-Qwen-7B-unsloth-bnb-4bit" : (
|
|
"unsloth/DeepSeek-R1-Distill-Qwen-7B",
|
|
"deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
|
|
"unsloth/DeepSeek-R1-Distill-Qwen-7B-bnb-4bit",
|
|
),
|
|
"unsloth/DeepSeek-R1-Distill-Qwen-1.5B-unsloth-bnb-4bit" : (
|
|
"unsloth/DeepSeek-R1-Distill-Qwen-1.5B",
|
|
"deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
|
|
"unsloth/DeepSeek-R1-Distill-Qwen-1.5B-bnb-4bit",
|
|
),
|
|
"unsloth/DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit" : (
|
|
"unsloth/DeepSeek-R1-Distill-Llama-8B",
|
|
"deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
|
|
"unsloth/DeepSeek-R1-Distill-Llama-8B-bnb-4bit",
|
|
),
|
|
"unsloth/DeepSeek-R1-Distill-Llama-70B-bnb-4bit" : (
|
|
"unsloth/DeepSeek-R1-Distill-Llama-70B",
|
|
"deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
|
|
),
|
|
"unsloth/Mistral-Small-24B-Base-2501-unsloth-bnb-4bit" : (
|
|
"unsloth/Mistral-Small-24B-Base",
|
|
"mistralai/Mistral-Small-24B-Base-2501",
|
|
"unsloth/Mistral-Small-24B-Base-2501-bnb-4bit",
|
|
),
|
|
"unsloth/Mistral-Small-24B-Instruct-2501-unsloth-bnb-4bit" : (
|
|
"unsloth/Mistral-Small-24B-Instruct",
|
|
"mistralai/Mistral-Small-24B-Instruct-2501",
|
|
"unsloth/Mistral-Small-24B-Instruct-2501-bnb-4bit",
|
|
),
|
|
"unsloth/Qwen2.5-VL-3B-Instruct-unsloth-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-VL-3B-Instruct",
|
|
"Qwen/Qwen2.5-VL-3B-Instruct",
|
|
"unsloth/Qwen2.5-VL-3B-Instruct-bnb-4bit",
|
|
),
|
|
"unsloth/Qwen2.5-VL-7B-Instruct-unsloth-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-VL-7B-Instruct",
|
|
"Qwen/Qwen2.5-VL-7B-Instruct",
|
|
"unsloth/Qwen2.5-VL-7B-Instruct-bnb-4bit",
|
|
),
|
|
"unsloth/Qwen2.5-VL-72B-Instruct-unsloth-bnb-4bit" : (
|
|
"unsloth/Qwen2.5-VL-72B-Instruct",
|
|
"Qwen/Qwen2.5-VL-72B-Instruct",
|
|
"unsloth/Qwen2.5-VL-72B-Instruct-bnb-4bit",
|
|
),
|
|
}
|
|
|
|
INT_TO_FLOAT_MAPPER = {}
|
|
FLOAT_TO_INT_MAPPER = {}
|
|
MAP_TO_UNSLOTH_16bit = {}
|
|
|
|
for key, values in __INT_TO_FLOAT_MAPPER.items():
|
|
INT_TO_FLOAT_MAPPER[key] = values[0]
|
|
|
|
for value in values:
|
|
FLOAT_TO_INT_MAPPER[value] = key
|
|
pass
|
|
|
|
# Map to Unsloth version for 16bit versions
|
|
if len(values) == 2:
|
|
if values[0].startswith("unsloth"):
|
|
MAP_TO_UNSLOTH_16bit[values[1]] = values[0]
|
|
MAP_TO_UNSLOTH_16bit[values[1].lower()] = values[0]
|
|
pass
|
|
elif len(values) == 3:
|
|
# Dynamic Unsloth quantization
|
|
if values[0].startswith("unsloth"):
|
|
MAP_TO_UNSLOTH_16bit[values[1]] = values[0]
|
|
MAP_TO_UNSLOTH_16bit[values[1].lower()] = values[0]
|
|
MAP_TO_UNSLOTH_16bit[values[2]] = values[0]
|
|
MAP_TO_UNSLOTH_16bit[values[2].lower()] = values[0]
|
|
pass
|
|
pass
|
|
|
|
# Get lowercased
|
|
lowered_key = key.lower()
|
|
INT_TO_FLOAT_MAPPER[lowered_key] = values[0].lower()
|
|
|
|
for value in values:
|
|
FLOAT_TO_INT_MAPPER[value.lower()] = lowered_key
|
|
pass
|
|
pass
|