Bug Fixes (#1774)
* Update rl.py * Update tokenizer_utils.py * Auto patching * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update rl.py * Update tokenizer_utils.py * Update rl.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_utils.py * Update tokenizer_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 tokenizer_utils.py * Update rl.py * Update rl.py * Update rl.py * max seq length * Update rl.py * Update rl.py * Patching * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * NEFTune * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Extra replacements * Update rl_replacements.py * Update rl.py * extra RL replacements * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update llama.py * Update rl_replacements.py * Update _utils.py * Update loader_utils.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * autocast * Update rl_replacements.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update llama.py * Update rl_replacements.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update rl_replacements.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update pyproject.toml * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update llama.py * Update _utils.py * Update llama.py * Update _utils.py * Update rl_replacements.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update rl_replacements.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * GRPO optimized * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Selective Log softmax * Fix GRPO bsz * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Fix TRL * Metrics GRPO * Update rl_replacements.py * Update rl_replacements.py * No compile * Update rl.py * Remove docs * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * llama-quantize on WINDOWS WSL error fix - edit save.py (gguf saving breaks) (#1649) * edit save.py to fix gguf saving breaks. * add check for .exe or not exe file extension for linux and windows * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * unsloth_num_chunks * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py (#1754) Fix typo in comment: know -> now. This was printed when running the Llama3.1_(8B)-GRPO.ipynb example notebook, so I'd expect others to run into it as well. * Optional logits * 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_replacements.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * fix an import error (#1767) * fix an import error * Delete .gitignore * Update loader.py * Update save.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * SamplingParams * Convert mask to float (#1762) * [Windows Support] Add latest `xformers` wheels to pyproject.toml (#1753) * Add latest xformers * Add a couple of lines to docs * vLLMSamplingParams * Update __init__.py * default num_chunks == -1 * Versioning * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update _utils.py * Update rl_replacements.py * Update rl_replacements.py * Update pyproject.toml * Update pyproject.toml --------- Co-authored-by: Gennadii Manzhos <105049664+everythingisc00l@users.noreply.github.com> Co-authored-by: Seth Weidman <seth@sethweidman.com> Co-authored-by: Nino Risteski <95188570+NinoRisteski@users.noreply.github.com> Co-authored-by: Edd <68678137+Erland366@users.noreply.github.com> Co-authored-by: Ben <6579034+versipellis@users.noreply.github.com>
This commit is contained in:
Daniel Han
GitHub
parent
02c19d97f9
commit
661859fff3
4 changed files with 16 additions and 9 deletions
|
|
@ -39,7 +39,7 @@ triton = [
|
|||
"triton @ https://github.com/woct0rdho/triton-windows/releases/download/v3.1.0-windows.post5/triton-3.1.0-cp312-cp312-win_amd64.whl ; python_version=='3.12' and platform_system == 'Windows'",
|
||||
]
|
||||
huggingface = [
|
||||
"unsloth_zoo>=2025.2.6",
|
||||
"unsloth_zoo>=2025.2.7",
|
||||
"packaging",
|
||||
"tyro",
|
||||
"transformers>=4.46.1,!=4.47.0",
|
||||
|
|
@ -50,7 +50,7 @@ huggingface = [
|
|||
"wheel>=0.42.0",
|
||||
"numpy",
|
||||
"accelerate>=0.34.1",
|
||||
"trl>=0.7.9,!=0.9.0,!=0.9.1,!=0.9.2,!=0.9.3",
|
||||
"trl>=0.7.9,!=0.9.0,!=0.9.1,!=0.9.2,!=0.9.3,!=0.15.0",
|
||||
"peft>=0.7.1,!=0.11.0",
|
||||
"protobuf<4.0.0",
|
||||
"huggingface_hub",
|
||||
|
|
@ -348,7 +348,7 @@ colab-ampere-torch220 = [
|
|||
"flash-attn>=2.6.3",
|
||||
]
|
||||
colab-new = [
|
||||
"unsloth_zoo>=2025.2.6",
|
||||
"unsloth_zoo>=2025.2.7",
|
||||
"packaging",
|
||||
"tyro",
|
||||
"transformers>=4.46.1,!=4.47.0",
|
||||
|
|
@ -366,7 +366,7 @@ colab-new = [
|
|||
]
|
||||
colab-no-deps = [
|
||||
"accelerate>=0.34.1",
|
||||
"trl>=0.7.9,!=0.9.0,!=0.9.1,!=0.9.2,!=0.9.3",
|
||||
"trl>=0.7.9,!=0.9.0,!=0.9.1,!=0.9.2,!=0.9.3,!=0.15.0",
|
||||
"peft>=0.7.1",
|
||||
"xformers",
|
||||
"bitsandbytes>=0.46.1",
|
||||
|
|
|
|||
|
|
@ -143,6 +143,11 @@ transformers_training_args_logger.addFilter(HideLoggingMessage("The speedups"))
|
|||
transformers_training_args_logger.addFilter(HideLoggingMessage("torch.distributed"))
|
||||
del transformers_training_args_logger
|
||||
|
||||
# No label_names provided for model class
|
||||
from transformers.trainer import logger as transformers_trainer_logger
|
||||
transformers_trainer_logger.addFilter(HideLoggingMessage("No label_names"))
|
||||
del transformers_trainer_logger
|
||||
|
||||
# Using the default loss: `ForCausalLMLoss`.
|
||||
try:
|
||||
from transformers.modeling_utils import logger as transformers_modeling_utils_logger
|
||||
|
|
|
|||
|
|
@ -725,8 +725,9 @@ def LlamaModel_fast_forward(
|
|||
past_key_values_length,
|
||||
sliding_window = getattr(self.config, "sliding_window", None),
|
||||
)
|
||||
if attention_mask is not None:
|
||||
attention_mask = attention_mask.to(torch.bool)
|
||||
# Must NOT convert to bool - weirdly this causes stuff to error out!
|
||||
# if attention_mask is not None:
|
||||
# attention_mask = attention_mask.to(torch.bool)
|
||||
pass
|
||||
|
||||
hidden_states = inputs_embeds
|
||||
|
|
|
|||
|
|
@ -164,10 +164,11 @@ RL_FUNCTIONS["grpo_trainer"].append(grpo_trainer__prepare_inputs)
|
|||
# Remove _move_model_to_vllm
|
||||
def grpo_trainer__move_model_to_vllm(function_name, function):
|
||||
if function_name != "_move_model_to_vllm": return function
|
||||
|
||||
def _move_model_to_vllm(self, *args, **kwargs): return None
|
||||
|
||||
# .*? matches first match. .+? matches final match.
|
||||
replacement = "def _move_model_to_vllm(self, *args, **kwargs): return None\n"
|
||||
return " "*function.find("def") + replacement
|
||||
function = inspect.getsource(_move_model_to_vllm)
|
||||
return function
|
||||
pass
|
||||
RL_FUNCTIONS["grpo_trainer"].append(grpo_trainer__move_model_to_vllm)
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue