Bug fixes (#1920)
* 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 * Export Model to ollama.com (#1648) * Ollama Export Model to ollama.com Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in> * Check for model_name Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in> * subprocess use instead of requests | added check for ollama server Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in> * create_ollama_model Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in> * create_ollama_model | fix Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in> * Push to Ollama Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in> --------- Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in> * Update cross_entropy_loss.py * torch_cuda_device * Update utils.py * Update utils.py * Update utils.py * device * device * Update loader.py * Update llama.py * Update README.md * 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 llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update utils.py * Update utils.py * Update utils.py * Update utils.py * __version__ * Update rl.py * Bug fixes * Bug fixes * Update llama.py * Update _utils.py * _wrap_fast_inference * 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 _utils.py * SFT dataset prepare * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update llama.py * Update llama.py * Update utils.py * bug fix * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update __init__.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update rl.py * Update rl.py * Update rl.py * Update _utils.py * Update __init__.py * Update _utils.py * Version * versioning * Update _utils.py * Update llama.py * Update llama.py --------- Signed-off-by: Jyotin Goel <b22ai063@iitj.ac.in> 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> Co-authored-by: Jyotin Goel <120490013+gjyotin305@users.noreply.github.com>
This commit is contained in:
Daniel Han
GitHub
parent
83eaa2f087
commit
53d0ba079e
4 changed files with 7 additions and 11 deletions
|
|
@ -40,7 +40,7 @@ triton = [
|
|||
]
|
||||
|
||||
huggingface = [
|
||||
"unsloth_zoo>=2025.3.4",
|
||||
"unsloth_zoo>=2025.3.5",
|
||||
"packaging",
|
||||
"tyro",
|
||||
"transformers>=4.46.1,!=4.47.0",
|
||||
|
|
@ -354,7 +354,7 @@ colab-ampere-torch220 = [
|
|||
"flash-attn>=2.6.3",
|
||||
]
|
||||
colab-new = [
|
||||
"unsloth_zoo>=2025.3.4",
|
||||
"unsloth_zoo>=2025.3.5",
|
||||
"packaging",
|
||||
"tyro",
|
||||
"transformers>=4.46.1,!=4.47.0",
|
||||
|
|
|
|||
|
|
@ -198,7 +198,7 @@ pass
|
|||
# Check for unsloth_zoo
|
||||
try:
|
||||
unsloth_zoo_version = importlib_version("unsloth_zoo")
|
||||
if Version(unsloth_zoo_version) < Version("2025.3.4"):
|
||||
if Version(unsloth_zoo_version) < Version("2025.3.5"):
|
||||
try:
|
||||
os.system("pip install --upgrade --no-cache-dir --no-deps unsloth_zoo")
|
||||
except:
|
||||
|
|
|
|||
|
|
@ -12,7 +12,7 @@
|
|||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
__version__ = "2025.3.6"
|
||||
__version__ = "2025.3.7"
|
||||
|
||||
__all__ = [
|
||||
"SUPPORTS_BFLOAT16",
|
||||
|
|
@ -1052,8 +1052,7 @@ def _unsloth_pre_compute_loss(self, model, inputs, *args, **kwargs):
|
|||
|
||||
# Get gradient accumulation steps if possible
|
||||
if num_items_in_batch is None and \
|
||||
getattr(self, "args", {}).get("gradient_accumulation_steps", 1) != 1:
|
||||
|
||||
getattr(getattr(self, "args", self), "gradient_accumulation_steps", 1) != 1:
|
||||
name = (model.base_model.model if hasattr(model, "base_model") else model).__class__.__name__
|
||||
logger.warning_once(
|
||||
f"Unsloth: Not an error, but {name} does not accept `num_items_in_batch`.\n"\
|
||||
|
|
|
|||
|
|
@ -1843,7 +1843,7 @@ class FastLlamaModel:
|
|||
else:
|
||||
inner_training_loop = Trainer._original_training_loop
|
||||
except:
|
||||
raise RuntimeError('Unsloth currently does not support multi GPU setups - but we are working on it!')
|
||||
raise RuntimeError('Unsloth: Unsuccessfully patched inner_training_loop')
|
||||
pass
|
||||
|
||||
import transformers.trainer
|
||||
|
|
@ -1869,7 +1869,7 @@ class FastLlamaModel:
|
|||
f"{chr(92)} / Data Parallel GPUs = {args.world_size} | Total batch size ({self._train_batch_size} x {args.gradient_accumulation_steps} x {args.world_size}) = {total_train_batch_size:,}\\n"\\
|
||||
f' "-____-" Trainable parameters = {get_model_param_count(model, trainable_only=True):,}/{get_model_param_count(model):,} ({get_model_param_count(model, trainable_only=True)/get_model_param_count(model)*100:.2f}% trained)'
|
||||
logger.warning(debug_info)
|
||||
import subprocess, re, gc
|
||||
import gc
|
||||
for _ in range(3):
|
||||
gc.collect()
|
||||
torch.cuda.empty_cache()"""
|
||||
|
|
@ -1897,9 +1897,6 @@ class FastLlamaModel:
|
|||
"_inner_training_loop",
|
||||
"_fast_inner_training_loop", 1,
|
||||
)
|
||||
exec(inner_training_loop, globals())
|
||||
|
||||
Trainer._inner_training_loop = _fast_inner_training_loop
|
||||
inner_training_loop = inner_training_loop.replace(
|
||||
"is_torch_tpu_available()",
|
||||
"False",
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue