GRPO Bug fixes (#1623)
* 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 67bb995878.
* 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
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* dim fix
* Update _utils.py
* Torch 2.6 support
* 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
* Faster inference?
* Update llama.py
* Update llama.py
* Update utils.py
* Update llama.py
* Update llama.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
* Update utils.py
* Update utils.py
* Update utils.py
* Update utils.py
* Update mapper.py
* Fast Inference via vLLM
* Update llama.py
* Update llama.py
* Update utils.py
* Create rl.py
* PatchRL
* Update rl.py
* Update rl.py
* Update rl.py
* PatchRLStatistics
* Update rl.py
* Update rl.py
* Update rl.py
* Update utils.py
* Update utils.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* RL metrics
* Update rl.py
* RL metrics
* Update __init__.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update chat_templates.py
* Update mapper.py
* Fp8 cache
* Update llama.py
* Update llama.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update __init__.py
* Update loader.py
* Update rl.py
* Update rl.py
* Update _utils.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>
This commit is contained in:
Daniel Han
GitHub
parent
7e55349bfa
commit
226a8ccefd
2 changed files with 4 additions and 4 deletions
|
|
@ -12,7 +12,7 @@
|
|||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
__version__ = "2025.2.3"
|
||||
__version__ = "2025.2.4"
|
||||
|
||||
__all__ = [
|
||||
"SUPPORTS_BFLOAT16",
|
||||
|
|
|
|||
|
|
@ -47,8 +47,8 @@ def PatchRL(FastLanguageModel):
|
|||
from contextlib import contextmanager
|
||||
|
||||
@contextmanager
|
||||
def unsloth_unwrap_model_for_generation(model, accelerator):
|
||||
with unwrap_model_for_generation(model, accelerator) as unwrapped_model:
|
||||
def unsloth_unwrap_model_for_generation(model, *args, **kwargs):
|
||||
with unwrap_model_for_generation(model, *args, **kwargs) as unwrapped_model:
|
||||
# Put the model in inference mode.
|
||||
FastLanguageModel.for_inference(unwrapped_model)
|
||||
|
||||
|
|
@ -364,7 +364,7 @@ def _patch_trl_rl_trainers(trainer_file = "grpo_trainer"):
|
|||
lora_name = trainer_file + "_lora_model"
|
||||
source = re.sub(
|
||||
r"(self\.llm\.(?:generate|chat)\([^\)]{1,})\)",
|
||||
r"\1, lora_request = model.load_lora('" + lora_name + r"', load_tensors = True))",
|
||||
r"\1, lora_request = self.model.load_lora('" + lora_name + r"', load_tensors = True))",
|
||||
source
|
||||
)
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue