Update modeling_iquestcoder.py

modeling_iquestcoder.py

@@ -1,11 +1,28 @@
-"""IQuestCoder model implementation.
-
-This implementation combines ideas from:
-- LLaMA: Core architecture and forward pass (for compatibility)
-- OLMo: QKV clipping for training stability
-- Qwen2: Sliding window attention support
-
-The forward pass is fully compatible with LLaMA weights.
+"""
+Modified MIT License 
+
+Software Copyright© 2025 IQuest Research
+
+Our only modification is that, if the Software (or any derivative works
+thereof) is used for any of your commercial products or services, you shall
+prominently display "IQuest Coder" on the user interface of such product or
+service.
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 """
 
 from typing import Callable, List, Optional, Tuple, Union
@@ -31,7 +48,6 @@ from transformers.modeling_rope_utils import ROPE_INIT_FUNCTIONS, dynamic_rope_u
 from transformers.modeling_utils import ALL_ATTENTION_FUNCTIONS, PreTrainedModel
 from transformers.processing_utils import Unpack
 from transformers.utils import (
-    LossKwargs,
     auto_docstring,
     can_return_tuple,
     is_torch_flex_attn_available,
@@ -688,10 +704,6 @@ class IQuestCoderModel(IQuestCoderPreTrainedModel):
 # Model Heads
 # =============================================================================
 
-class KwargsForCausalLM(FlashAttentionKwargs, LossKwargs):
-    ...
-
-
 @auto_docstring
 class IQuestCoderForCausalLM(IQuestCoderPreTrainedModel, GenerationMixin):
     """IQuestCoder Model with a language modeling head on top for causal LM."""
@@ -742,7 +754,7 @@ class IQuestCoderForCausalLM(IQuestCoderPreTrainedModel, GenerationMixin):
         output_hidden_states: Optional[bool] = None,
         cache_position: Optional[torch.LongTensor] = None,
         logits_to_keep: Union[int, torch.Tensor] = 0,
-        **kwargs: Unpack[KwargsForCausalLM],
+        **kwargs
     ) -> CausalLMOutputWithPast:
         r"""
         Args: