lalamo 0.5.11__py3-none-any.whl → 0.5.12__py3-none-any.whl

lalamo/__init__.py

@@ -15,7 +15,7 @@ from lalamo.speculator import (
     SpeculatorTrainingEvent,
 )
 
-__version__ = "0.5.11"
+__version__ = "0.5.12"
 
 __all__ = [
     "AssistantMessage",

lalamo/model_import/decoder_configs/huggingface/gemma3.py

@@ -46,7 +46,6 @@ class HFGemma3TextConfigRaw:
     model_type: Literal["gemma3_text"]
     num_hidden_layers: int
     sliding_window: int
-    sliding_window_pattern: int
     rms_norm_eps: float = 1e-06
     query_pre_attn_scalar: float = 256.0
     attention_bias: bool = False
@@ -55,6 +54,7 @@ class HFGemma3TextConfigRaw:
     attn_logit_softcapping: float | None = None
     head_dim: int = 256
     max_position_embeddings: int = 131072
+    sliding_window_pattern: int = 6
     rope_theta: float = 1000000.0
     rope_local_base_freq: float = 10000.0
     rope_scaling: GemmaRoPEScalingConfig | YarnRopeScalingConfig | None = None

lalamo/model_import/loaders/huggingface.py

@@ -350,9 +350,9 @@ def load_attention(
     weights_dict: Mapping[str, Array],
     path: ParameterPath,
 ) -> Attention:
-    if (path / "o_proj.weight") in weights_dict:
+    if (path / "o_proj.weight") in weights_dict or (path / "o_proj.qweight") in weights_dict:
         o_proj_name = "o_proj"
-    elif (path / "out_proj.weight") in weights_dict:
+    elif (path / "out_proj.weight") in weights_dict or (path / "out_proj.qweight") in weights_dict:
         o_proj_name = "out_proj"
     else:
         raise NotImplementedError("Can't determine attention output projection name")

{lalamo-0.5.11.dist-info → lalamo-0.5.12.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: lalamo
-Version: 0.5.11
+Version: 0.5.12
 Summary: JAX library for optimization and export of models for use with the UZU inference engine.
 Requires-Python: <4,>=3.12
 Description-Content-Type: text/markdown

{lalamo-0.5.11.dist-info → lalamo-0.5.12.dist-info}/RECORD

@@ -1,4 +1,4 @@
-lalamo/__init__.py,sha256=YYirmrwul4QLFCnBJpYyq8Os5sFQNn-9OxTjd0CbSd8,815
+lalamo/__init__.py,sha256=Q9W7Wur0iL4StzN99Y70CLGeiCHriTxjg50OLzXIDLw,815
 lalamo/common.py,sha256=5NUFD26yQgOnEEk3LaQnce8n-VwJxILkEpFesHZhtQU,3820
 lalamo/main.py,sha256=GgUT7lT48-XQuAEH7qzsDKG8Lx9iBf-sYBIRhZL9q7E,23978
 lalamo/message_processor.py,sha256=bSUAQg7CemLTnBV4LtPxJBicAalruDCA-JXjkTYPZ8U,5797
@@ -20,7 +20,7 @@ lalamo/model_import/decoder_configs/executorch.py,sha256=fTEG_j-7d8riR3Fu_H5tHDj
 lalamo/model_import/decoder_configs/huggingface/__init__.py,sha256=AboZJgZxOuIigPShskj-FqBkBqwlJZoKHP0RDqx-MyY,696
 lalamo/model_import/decoder_configs/huggingface/common.py,sha256=YYIDEQy8x7lqL2qtxUHrNqfjZEiizBZ_26sTqOzjRtQ,3792
 lalamo/model_import/decoder_configs/huggingface/gemma2.py,sha256=g8LH_GlSNyL04WWi596zI0rWsD3ahnfNjDk-9zZNcDE,4759
-lalamo/model_import/decoder_configs/huggingface/gemma3.py,sha256=aSZ0TtpgDYA10rHi8eD0C_Jsn48siM_HXqfZ4O7nh94,8372
+lalamo/model_import/decoder_configs/huggingface/gemma3.py,sha256=EYkcsRUKVQqPFyL8dZuocDVAUaM8d9dr_aMh5-jTvTM,8376
 lalamo/model_import/decoder_configs/huggingface/gpt_oss.py,sha256=MBCoPbuWyzbJiBRtHOtpaPHJjQ1UVCAYcVrfIejTnlQ,7446
 lalamo/model_import/decoder_configs/huggingface/lfm2.py,sha256=vrBMxtiKEg0eHNDL_bWM9odlrsab7jlMXEY8vjEB7-c,7595
 lalamo/model_import/decoder_configs/huggingface/llama.py,sha256=UPeQiz2Dix8YaZYRxn9z44OZJ6c4xBQmcUZcM0Ymvh4,6934
@@ -32,7 +32,7 @@ lalamo/model_import/decoder_configs/huggingface/qwen3.py,sha256=lySVO-TvusAYUjDn
 lalamo/model_import/loaders/__init__.py,sha256=3THc1wQ4EPBzQkL_4EaKCa7Ev5Z7oczcvc4AHy9v5EI,228
 lalamo/model_import/loaders/common.py,sha256=kkugV-bMQlN1zvGHoj3uc7z0FbXKoMtXEBTvyu4KxK4,1844
 lalamo/model_import/loaders/executorch.py,sha256=t2Ey_mBMNC8bTSTdYWjuGXdPTRoohFlYrqtWyNkBU_8,9219
-lalamo/model_import/loaders/huggingface.py,sha256=_vFAgz6ZR8386VIuhWAY88nJ8qoTDawCREBsRHQQmGo,32753
+lalamo/model_import/loaders/huggingface.py,sha256=nGaJDAB-2uK5z7XNYEpVDZcAoAZF-w3zs6xWOK7nzac,32845
 lalamo/model_import/loaders/utils.py,sha256=eiX3WKFRrAfBY-dugodscNInl5o5w3KmVcgma4atpGY,2456
 lalamo/model_import/model_specs/__init__.py,sha256=JISqwJkloQkGD2jvi1MakNEWapIwlNXXVi5giZyXB74,1275
 lalamo/model_import/model_specs/common.py,sha256=RLySCIkmGiA1IVZgLeemssMBMo4hMYMpmBjV0cRwBb4,6586
@@ -85,9 +85,9 @@ lalamo/speculator/estimator.py,sha256=4D8dPZCWsrpORb7y8pQ6VsiIg1Cblvvxe6gXCoYtcD
 lalamo/speculator/inference.py,sha256=5GntUgj0HQLeLn3HIHnVX8EEO0EBzmKeP5-_U7kdFAM,3670
 lalamo/speculator/ngram.py,sha256=95mdfAWhx4d5XOnOwhyhElnvcy6nlUjYhcbJzqDs414,5875
 lalamo/speculator/utils.py,sha256=0wZoMMIzzk0Q-3zq5H5f-JBplePNHxywndkrNtOJOyo,1697
-lalamo-0.5.11.dist-info/licenses/LICENSE,sha256=diHRfjSEJHD1nnEeMIfMRCjR3UERf8bT3eseD6b1ayA,1072
-lalamo-0.5.11.dist-info/METADATA,sha256=0uICfw4NXxiDgA8JIPaYiUnOlFcGxYe7NKbNP2ZejHE,3147
-lalamo-0.5.11.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-lalamo-0.5.11.dist-info/entry_points.txt,sha256=qli7qTfnBk5WP10rOGXXEckHMtt-atJMDWd8jN89Uks,43
-lalamo-0.5.11.dist-info/top_level.txt,sha256=VHvWL5JN5XRG36NsN_MieJ7EwRihEOrEjyDaTdFJ-aI,7
-lalamo-0.5.11.dist-info/RECORD,,
+lalamo-0.5.12.dist-info/licenses/LICENSE,sha256=diHRfjSEJHD1nnEeMIfMRCjR3UERf8bT3eseD6b1ayA,1072
+lalamo-0.5.12.dist-info/METADATA,sha256=dRj887UMuZ5JBHgriCILQxCKklC-ZNyAcsOLAwbbyrU,3147
+lalamo-0.5.12.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+lalamo-0.5.12.dist-info/entry_points.txt,sha256=qli7qTfnBk5WP10rOGXXEckHMtt-atJMDWd8jN89Uks,43
+lalamo-0.5.12.dist-info/top_level.txt,sha256=VHvWL5JN5XRG36NsN_MieJ7EwRihEOrEjyDaTdFJ-aI,7
+lalamo-0.5.12.dist-info/RECORD,,