knsimon commited on
Commit
bf33812
·
verified ·
1 Parent(s): 8a79182

teutonic clone submission

Browse files
config.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "QuasarForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoModelForCausalLM": "modeling_qwen3_5.QuasarForCausalLM",
9
+ "AutoConfig": "configuration_qwen3_5.QuasarConfig"
10
+ },
11
+ "bos_token_id": null,
12
+ "dtype": "bfloat16",
13
+ "eos_token_id": 248044,
14
+ "head_dim": 256,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 4096,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 12288,
19
+ "layer_types": [
20
+ "linear_attention",
21
+ "linear_attention",
22
+ "linear_attention",
23
+ "full_attention",
24
+ "linear_attention",
25
+ "linear_attention",
26
+ "linear_attention",
27
+ "full_attention",
28
+ "linear_attention",
29
+ "linear_attention",
30
+ "linear_attention",
31
+ "full_attention",
32
+ "linear_attention",
33
+ "linear_attention",
34
+ "linear_attention",
35
+ "full_attention",
36
+ "linear_attention",
37
+ "linear_attention",
38
+ "linear_attention",
39
+ "full_attention",
40
+ "linear_attention",
41
+ "linear_attention",
42
+ "linear_attention",
43
+ "full_attention",
44
+ "linear_attention",
45
+ "linear_attention",
46
+ "linear_attention",
47
+ "full_attention",
48
+ "linear_attention",
49
+ "linear_attention",
50
+ "linear_attention",
51
+ "full_attention"
52
+ ],
53
+ "linear_conv_kernel_dim": 4,
54
+ "linear_key_head_dim": 128,
55
+ "linear_num_key_heads": 16,
56
+ "linear_num_value_heads": 32,
57
+ "linear_value_head_dim": 128,
58
+ "max_position_embeddings": 2097152,
59
+ "model_type": "quasar_text",
60
+ "num_attention_heads": 16,
61
+ "num_hidden_layers": 32,
62
+ "num_key_value_heads": 4,
63
+ "pad_token_id": null,
64
+ "partial_rotary_factor": 0.25,
65
+ "rms_norm_eps": 1e-06,
66
+ "rope_parameters": {
67
+ "mrope_interleaved": true,
68
+ "mrope_section": [
69
+ 11,
70
+ 11,
71
+ 10
72
+ ],
73
+ "partial_rotary_factor": 0.25,
74
+ "rope_theta": 10000000,
75
+ "rope_type": "default"
76
+ },
77
+ "tie_word_embeddings": false,
78
+ "transformers_version": "5.9.0",
79
+ "use_cache": true,
80
+ "use_gla": true,
81
+ "use_nope": true,
82
+ "vocab_size": 248320,
83
+ "_name_or_path": "dendrite/teutonic-x",
84
+ "attn_output_gate": true,
85
+ "full_attention_interval": 4,
86
+ "mamba_ssm_dtype": "float32",
87
+ "mlp_only_layers": [],
88
+ "mtp_num_hidden_layers": 1,
89
+ "mtp_use_dedicated_embeddings": false
90
+ }
configuration_qwen3_5.py ADDED
@@ -0,0 +1,311 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
2
+ # This file was automatically generated from src/transformers/models/quasar/modular_quasar.py.
3
+ # Do NOT edit this file manually as any edits will be overwritten by the generation of
4
+ # the file from the modular. If any change should be done, please apply the change to the
5
+ # modular_quasar.py file directly. One of our CI enforces this.
6
+ # 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
7
+ # Copyright 2025 The Qwen Team and The HuggingFace Inc. team. All rights reserved.
8
+ #
9
+ # Licensed under the Apache License, Version 2.0 (the "License");
10
+ # you may not use this file except in compliance with the License.
11
+ # You may obtain a copy of the License at
12
+ #
13
+ # http://www.apache.org/licenses/LICENSE-2.0
14
+ #
15
+ # Unless required by applicable law or agreed to in writing, software
16
+ # distributed under the License is distributed on an "AS IS" BASIS,
17
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
18
+ # See the License for the specific language governing permissions and
19
+ # limitations under the License.
20
+ from transformers.configuration_utils import PreTrainedConfig, layer_type_validation
21
+ from transformers.modeling_rope_utils import RopeParameters
22
+
23
+
24
+ class QuasarTextConfig(PreTrainedConfig):
25
+ r"""
26
+ This is the configuration class to store the configuration of a [`QuasarTextModel`]. It is used to instantiate a
27
+ Quasar model according to the specified arguments, defining the model architecture.
28
+ Instantiating a configuration with the defaults will yield a similar configuration to that of
29
+ Qwen3.5-9B-Instruct [Qwen/Qwen3.5-9B-Instruct](https://huggingface.co/Qwen/Qwen3.5-9B-Instruct).
30
+
31
+ Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the
32
+ documentation from [`PreTrainedConfig`] for more information.
33
+
34
+
35
+ Args:
36
+ vocab_size (`int`, *optional*, defaults to 248320):
37
+ Vocabulary size of the model. Defines the number of different tokens that can be represented by the
38
+ `inputs_ids`.
39
+ hidden_size (`int`, *optional*, defaults to 4096):
40
+ Dimension of the hidden representations.
41
+ intermediate_size (`int`, *optional*, defaults to 12288):
42
+ Dimension of the MLP representations.
43
+ num_hidden_layers (`int`, *optional*, defaults to 32):
44
+ Number of hidden layers in the Transformer encoder.
45
+ num_attention_heads (`int`, *optional*, defaults to 16):
46
+ Number of attention heads for each attention layer in the Transformer encoder.
47
+ num_key_value_heads (`int`, *optional*, defaults to 4):
48
+ This is the number of key_value heads that should be used to implement Grouped Query Attention. If
49
+ `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
50
+ `num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When
51
+ converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
52
+ by meanpooling all the original heads within that group. For more details checkout [this
53
+ paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to `32`.
54
+ hidden_act (`str`, *optional*, defaults to `"silu"`):
55
+ The non-linear activation function in the decoder.
56
+ max_position_embeddings (`int`, *optional*, defaults to 32768):
57
+ The maximum sequence length that this model might ever be used with.
58
+ initializer_range (`float`, *optional*, defaults to 0.02):
59
+ The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
60
+ rms_norm_eps (`float`, *optional*, defaults to 1e-06):
61
+ The epsilon used by the rms normalization layers.
62
+ use_cache (`bool`, *optional*, defaults to `True`):
63
+ Whether or not the model should return the last key/values attentions (not used by all models). Only
64
+ relevant if `config.is_decoder=True`.
65
+ tie_word_embeddings (`bool`, *optional*, defaults to `False`):
66
+ Whether the model's input and output word embeddings should be tied.
67
+ rope_parameters (`RopeParameters`, *optional*):
68
+ Dictionary containing the configuration parameters for the RoPE embeddings. The dictionary should contain
69
+ a value for `rope_theta` and optionally parameters used for scaling in case you want to use RoPE
70
+ with longer `max_position_embeddings`.
71
+ attention_bias (`bool`, *optional*, defaults to `False`):
72
+ Whether to use a bias in the query, key, value and output projection layers during self-attention.
73
+ attention_dropout (`float`, *optional*, defaults to 0.0):
74
+ The dropout ratio for the attention probabilities.
75
+ head_dim (`int`, *optional*, defaults to 256):
76
+ Projection weights dimension in multi-head attention.
77
+ linear_conv_kernel_dim (`int`, *optional*, defaults to 4):
78
+ Kernel size of the convolution used in linear attention layers.
79
+ linear_key_head_dim (`int`, *optional*, defaults to 128):
80
+ Dimension of each key head in linear attention.
81
+ linear_value_head_dim (`int`, *optional*, defaults to 128):
82
+ Dimension of each value head in linear attention.
83
+ linear_num_key_heads (`int`, *optional*, defaults to 16):
84
+ Number of key heads used in linear attention layers.
85
+ linear_num_value_heads (`int`, *optional*, defaults to 32):
86
+ Number of value heads used in linear attention layers.
87
+ layer_types (`list[str]`, *optional*):
88
+ Types of each layer (attention or linear).
89
+ pad_token_id (`int`, *optional*):
90
+ Padding token id.
91
+ bos_token_id (`int`, *optional*):
92
+ Beginning of stream token id.
93
+ eos_token_id (`int`, *optional*):
94
+ End of stream token id.
95
+
96
+ ```python
97
+ >>> from transformers import QuasarTextModel, QuasarTextConfig
98
+
99
+ >>> # Initializing a Qwen3.5 style configuration
100
+ >>> configuration = QuasarTextConfig()
101
+
102
+ >>> # Initializing a model from the Qwen3.5-9B style configuration
103
+ >>> model = QuasarTextModel(configuration)
104
+
105
+ >>> # Accessing the model configuration
106
+ >>> configuration = model.config
107
+ ```
108
+ """
109
+
110
+ model_type = "quasar_text"
111
+ keys_to_ignore_at_inference = ["past_key_values"]
112
+
113
+ base_model_tp_plan = {
114
+ "layers.*.self_attn.q_proj": "colwise",
115
+ "layers.*.self_attn.k_proj": "colwise",
116
+ "layers.*.self_attn.v_proj": "colwise",
117
+ "layers.*.self_attn.o_proj": "rowwise",
118
+ "layers.*.mlp.gate_proj": "colwise",
119
+ "layers.*.mlp.up_proj": "colwise",
120
+ "layers.*.mlp.down_proj": "rowwise",
121
+ }
122
+ base_model_pp_plan = {
123
+ "embed_tokens": (["input_ids"], ["inputs_embeds"]),
124
+ "layers": (["hidden_states", "attention_mask"], ["hidden_states"]),
125
+ "norm": (["hidden_states"], ["hidden_states"]),
126
+ }
127
+ base_config_key = "text_config"
128
+
129
+ def __init__(
130
+ self,
131
+ vocab_size=248320,
132
+ hidden_size=4096,
133
+ intermediate_size=12288,
134
+ num_hidden_layers=32,
135
+ num_attention_heads=16,
136
+ num_key_value_heads=4,
137
+ hidden_act="silu",
138
+ max_position_embeddings=32768,
139
+ initializer_range=0.02,
140
+ rms_norm_eps=1e-6,
141
+ use_cache=True,
142
+ tie_word_embeddings=False,
143
+ rope_parameters: RopeParameters | dict[str, RopeParameters] | None = None,
144
+ attention_bias=False,
145
+ attention_dropout=0.0,
146
+ head_dim=256,
147
+ linear_conv_kernel_dim=4,
148
+ linear_key_head_dim=128,
149
+ linear_value_head_dim=128,
150
+ linear_num_key_heads=16,
151
+ linear_num_value_heads=32,
152
+ layer_types=None,
153
+ pad_token_id: int | None = None,
154
+ bos_token_id: int | None = None,
155
+ eos_token_id: int | None = None,
156
+ use_gla: bool = False,
157
+ use_nope: bool = False,
158
+ **kwargs,
159
+ ):
160
+ kwargs["ignore_keys_at_rope_validation"] = {"mrope_section", "mrope_interleaved"}
161
+ self.pad_token_id = pad_token_id
162
+ self.bos_token_id = bos_token_id
163
+ self.eos_token_id = eos_token_id
164
+ self.tie_word_embeddings = tie_word_embeddings
165
+ self.vocab_size = vocab_size
166
+ self.max_position_embeddings = max_position_embeddings
167
+ self.hidden_size = hidden_size
168
+ self.intermediate_size = intermediate_size
169
+ self.num_hidden_layers = num_hidden_layers
170
+ self.num_attention_heads = num_attention_heads
171
+ self.num_key_value_heads = num_key_value_heads
172
+ self.hidden_act = hidden_act
173
+ self.initializer_range = initializer_range
174
+ self.rms_norm_eps = rms_norm_eps
175
+ self.use_cache = use_cache
176
+ self.attention_bias = attention_bias
177
+ self.attention_dropout = attention_dropout
178
+ self.head_dim = head_dim
179
+ self.rope_parameters = rope_parameters
180
+ self.use_gla = use_gla
181
+ self.use_nope = use_nope
182
+ kwargs.setdefault("partial_rotary_factor", 0.25) # assign default for BC
183
+
184
+ self.layer_types = layer_types
185
+ if self.layer_types is None:
186
+ interval_pattern = kwargs.get("full_attention_interval", 4)
187
+ self.layer_types = [
188
+ "linear_attention" if bool((i + 1) % interval_pattern) else "full_attention"
189
+ for i in range(self.num_hidden_layers)
190
+ ]
191
+ layer_type_validation(self.layer_types, self.num_hidden_layers)
192
+
193
+ # linear attention part
194
+ self.linear_conv_kernel_dim = linear_conv_kernel_dim
195
+ self.linear_key_head_dim = linear_key_head_dim
196
+ self.linear_value_head_dim = linear_value_head_dim
197
+ self.linear_num_key_heads = linear_num_key_heads
198
+ self.linear_num_value_heads = linear_num_value_heads
199
+ super().__init__(**kwargs)
200
+
201
+
202
+ class QuasarVisionConfig(PreTrainedConfig):
203
+ model_type = "quasar"
204
+ base_config_key = "vision_config"
205
+
206
+ def __init__(
207
+ self,
208
+ depth=27,
209
+ hidden_size=1152,
210
+ hidden_act="gelu_pytorch_tanh",
211
+ intermediate_size=4304,
212
+ num_heads=16,
213
+ in_channels=3,
214
+ patch_size=16,
215
+ spatial_merge_size=2,
216
+ temporal_patch_size=2,
217
+ out_hidden_size=3584,
218
+ num_position_embeddings=2304,
219
+ initializer_range=0.02,
220
+ **kwargs,
221
+ ):
222
+ super().__init__(**kwargs)
223
+
224
+ self.depth = depth
225
+ self.hidden_size = hidden_size
226
+ self.hidden_act = hidden_act
227
+ self.intermediate_size = intermediate_size
228
+ self.num_heads = num_heads
229
+ self.in_channels = in_channels
230
+ self.patch_size = patch_size
231
+ self.spatial_merge_size = spatial_merge_size
232
+ self.temporal_patch_size = temporal_patch_size
233
+ self.out_hidden_size = out_hidden_size
234
+ self.num_position_embeddings = num_position_embeddings
235
+ self.initializer_range = initializer_range
236
+
237
+
238
+ class QuasarConfig(PreTrainedConfig):
239
+ r"""
240
+ This is the configuration class to store the configuration of a [`QuasarModel`]. It is used to instantiate a
241
+ Qwen3.5 model according to the specified arguments, defining the model architecture. Instantiating a configuration
242
+ with the defaults will yield a similar configuration to that of
243
+ Qwen3.5-9B-Instruct [Qwen/Qwen3.5-9B-Instruct](https://huggingface.co/Qwen/Qwen3.5-9B-Instruct).
244
+
245
+ Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the
246
+ documentation from [`PreTrainedConfig`] for more information.
247
+
248
+
249
+ Args:
250
+ text_config (`Union[PreTrainedConfig, dict]`, *optional*, defaults to `QuasarTextConfig`):
251
+ The config object or dictionary of the text backbone.
252
+ vision_config (`Union[PreTrainedConfig, dict]`, *optional*, defaults to `QuasarVisionConfig`):
253
+ The config object or dictionary of the vision backbone.
254
+ image_token_id (`int`, *optional*, defaults to 248056):
255
+ The image token index to encode the image prompt.
256
+ video_token_id (`int`, *optional*, defaults to 248057):
257
+ The video token index to encode the image prompt.
258
+ vision_start_token_id (`int`, *optional*, defaults to 248053):
259
+ The start token index to encode the image prompt.
260
+ vision_end_token_id (`int`, *optional*, defaults to 248054):
261
+ The end token index to encode the image prompt.
262
+ tie_word_embeddings (`bool`, *optional*, defaults to `False`):
263
+ Whether to tie the word embeddings.
264
+
265
+ ```python
266
+ >>> from transformers import QuasarForConditionalGeneration, QuasarConfig
267
+
268
+ >>> # Initializing a Qwen3.5 style configuration
269
+ >>> configuration = QuasarConfig()
270
+
271
+ >>> # Initializing a model from the Qwen3.5-9B style configuration
272
+ >>> model = QuasarForConditionalGeneration(configuration)
273
+
274
+ >>> # Accessing the model configuration
275
+ >>> configuration = model.config
276
+ ```"""
277
+
278
+ model_type = "quasar"
279
+ sub_configs = {"vision_config": QuasarVisionConfig, "text_config": QuasarTextConfig}
280
+ keys_to_ignore_at_inference = ["past_key_values"]
281
+
282
+ def __init__(
283
+ self,
284
+ text_config=None,
285
+ vision_config=None,
286
+ image_token_id=248056,
287
+ video_token_id=248057,
288
+ vision_start_token_id=248053,
289
+ vision_end_token_id=248054,
290
+ tie_word_embeddings=False,
291
+ **kwargs,
292
+ ):
293
+ if isinstance(vision_config, dict):
294
+ self.vision_config = self.sub_configs["vision_config"](**vision_config)
295
+ elif vision_config is None:
296
+ self.vision_config = self.sub_configs["vision_config"]()
297
+
298
+ if isinstance(text_config, dict):
299
+ self.text_config = self.sub_configs["text_config"](**text_config)
300
+ elif text_config is None:
301
+ self.text_config = self.sub_configs["text_config"]()
302
+
303
+ self.image_token_id = image_token_id
304
+ self.video_token_id = video_token_id
305
+ self.vision_start_token_id = vision_start_token_id
306
+ self.vision_end_token_id = vision_end_token_id
307
+ self.tie_word_embeddings = tie_word_embeddings
308
+ super().__init__(**kwargs)
309
+
310
+
311
+ __all__ = ["QuasarConfig", "QuasarTextConfig"]
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 248044
5
+ ],
6
+ "output_attentions": false,
7
+ "output_hidden_states": false,
8
+ "pad_token_id": 248044,
9
+ "transformers_version": "5.14.1",
10
+ "use_cache": true
11
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77edd21e28b203eef5c4bad05650b5c61b377be34e1cb39c7f37f8e97de2af0f
3
+ size 4505889768
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9cb47647b428510d4901879980a2624a40b757a48fe93767c0339b361383b2a
3
+ size 4489050536
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8928724eeea5757a0ad508b711e1f24f7ea4e189e602d941741cd3f624d20ec3
3
+ size 4493087952
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daeb4d16a68a0d28cabf5c182979627a22639b1700bf06afb2feaec6973cedc7
3
+ size 3716098952
model.safetensors.index.json ADDED
@@ -0,0 +1,459 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 8602037248,
4
+ "total_size": 17204074496
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00001-of-00004.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.linear_attn.A_log": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.linear_attn.norm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.linear_attn.A_log": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.linear_attn.dt_bias": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.1.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.1.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.1.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.1.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.linear_attn.A_log": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.10.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.10.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.10.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.10.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.10.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.11.self_attn.gla.g_norm_swish_gate.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.11.self_attn.gla.g_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.11.self_attn.gla.gk_proj.0.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.11.self_attn.gla.gk_proj.1.bias": "model-00002-of-00004.safetensors",
60
+ "model.layers.11.self_attn.gla.gk_proj.1.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.11.self_attn.gla.k_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.11.self_attn.gla.o_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.11.self_attn.gla.q_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.11.self_attn.gla.v_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.12.linear_attn.A_log": "model-00002-of-00004.safetensors",
67
+ "model.layers.12.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.12.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
69
+ "model.layers.12.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.12.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.12.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
72
+ "model.layers.12.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
73
+ "model.layers.12.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
74
+ "model.layers.12.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
75
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
76
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
77
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
78
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
79
+ "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors",
80
+ "model.layers.13.linear_attn.A_log": "model-00003-of-00004.safetensors",
81
+ "model.layers.13.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
82
+ "model.layers.13.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
83
+ "model.layers.13.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
84
+ "model.layers.13.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
85
+ "model.layers.13.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
86
+ "model.layers.13.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
87
+ "model.layers.13.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
88
+ "model.layers.13.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
89
+ "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
90
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
91
+ "model.layers.13.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
92
+ "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
93
+ "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors",
94
+ "model.layers.14.linear_attn.A_log": "model-00003-of-00004.safetensors",
95
+ "model.layers.14.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
96
+ "model.layers.14.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
97
+ "model.layers.14.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
98
+ "model.layers.14.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
99
+ "model.layers.14.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
100
+ "model.layers.14.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
101
+ "model.layers.14.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
102
+ "model.layers.14.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
103
+ "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
104
+ "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
105
+ "model.layers.14.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
106
+ "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
107
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
108
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
109
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
110
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
111
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
112
+ "model.layers.15.self_attn.gla.g_norm_swish_gate.weight": "model-00003-of-00004.safetensors",
113
+ "model.layers.15.self_attn.gla.g_proj.weight": "model-00003-of-00004.safetensors",
114
+ "model.layers.15.self_attn.gla.gk_proj.0.weight": "model-00003-of-00004.safetensors",
115
+ "model.layers.15.self_attn.gla.gk_proj.1.bias": "model-00003-of-00004.safetensors",
116
+ "model.layers.15.self_attn.gla.gk_proj.1.weight": "model-00003-of-00004.safetensors",
117
+ "model.layers.15.self_attn.gla.k_proj.weight": "model-00003-of-00004.safetensors",
118
+ "model.layers.15.self_attn.gla.o_proj.weight": "model-00003-of-00004.safetensors",
119
+ "model.layers.15.self_attn.gla.q_proj.weight": "model-00003-of-00004.safetensors",
120
+ "model.layers.15.self_attn.gla.v_proj.weight": "model-00003-of-00004.safetensors",
121
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
122
+ "model.layers.16.linear_attn.A_log": "model-00003-of-00004.safetensors",
123
+ "model.layers.16.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
124
+ "model.layers.16.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
125
+ "model.layers.16.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.16.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.16.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
128
+ "model.layers.16.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.16.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.16.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
132
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
134
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.17.linear_attn.A_log": "model-00003-of-00004.safetensors",
137
+ "model.layers.17.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.17.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
139
+ "model.layers.17.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.17.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.17.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.17.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.17.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.17.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.18.linear_attn.A_log": "model-00003-of-00004.safetensors",
151
+ "model.layers.18.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.18.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
153
+ "model.layers.18.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.18.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.18.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.18.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.18.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.18.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.19.self_attn.gla.g_norm_swish_gate.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.19.self_attn.gla.g_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.19.self_attn.gla.gk_proj.0.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.19.self_attn.gla.gk_proj.1.bias": "model-00003-of-00004.safetensors",
172
+ "model.layers.19.self_attn.gla.gk_proj.1.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.19.self_attn.gla.k_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.19.self_attn.gla.o_proj.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.19.self_attn.gla.q_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.19.self_attn.gla.v_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.2.input_layernorm.weight": "model-00002-of-00004.safetensors",
178
+ "model.layers.2.linear_attn.A_log": "model-00002-of-00004.safetensors",
179
+ "model.layers.2.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
180
+ "model.layers.2.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
181
+ "model.layers.2.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
182
+ "model.layers.2.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
183
+ "model.layers.2.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
184
+ "model.layers.2.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
185
+ "model.layers.2.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
186
+ "model.layers.2.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
187
+ "model.layers.2.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
188
+ "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
189
+ "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
190
+ "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
191
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.20.linear_attn.A_log": "model-00003-of-00004.safetensors",
193
+ "model.layers.20.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.20.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
195
+ "model.layers.20.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.20.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.20.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.20.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.20.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.20.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.21.linear_attn.A_log": "model-00003-of-00004.safetensors",
207
+ "model.layers.21.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.21.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
209
+ "model.layers.21.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.21.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.21.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.21.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.21.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.21.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
218
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
219
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.22.linear_attn.A_log": "model-00003-of-00004.safetensors",
221
+ "model.layers.22.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors",
222
+ "model.layers.22.linear_attn.dt_bias": "model-00003-of-00004.safetensors",
223
+ "model.layers.22.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors",
224
+ "model.layers.22.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.22.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.22.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.22.linear_attn.norm.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.22.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.22.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
232
+ "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
233
+ "model.layers.23.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
+ "model.layers.23.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
236
+ "model.layers.23.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
237
+ "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.23.self_attn.gla.g_norm_swish_gate.weight": "model-00004-of-00004.safetensors",
239
+ "model.layers.23.self_attn.gla.g_proj.weight": "model-00004-of-00004.safetensors",
240
+ "model.layers.23.self_attn.gla.gk_proj.0.weight": "model-00004-of-00004.safetensors",
241
+ "model.layers.23.self_attn.gla.gk_proj.1.bias": "model-00004-of-00004.safetensors",
242
+ "model.layers.23.self_attn.gla.gk_proj.1.weight": "model-00004-of-00004.safetensors",
243
+ "model.layers.23.self_attn.gla.k_proj.weight": "model-00004-of-00004.safetensors",
244
+ "model.layers.23.self_attn.gla.o_proj.weight": "model-00004-of-00004.safetensors",
245
+ "model.layers.23.self_attn.gla.q_proj.weight": "model-00004-of-00004.safetensors",
246
+ "model.layers.23.self_attn.gla.v_proj.weight": "model-00004-of-00004.safetensors",
247
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00004.safetensors",
248
+ "model.layers.24.linear_attn.A_log": "model-00004-of-00004.safetensors",
249
+ "model.layers.24.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
250
+ "model.layers.24.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
251
+ "model.layers.24.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
252
+ "model.layers.24.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
253
+ "model.layers.24.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
254
+ "model.layers.24.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
255
+ "model.layers.24.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
256
+ "model.layers.24.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
257
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
258
+ "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
259
+ "model.layers.24.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
260
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
261
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00004.safetensors",
262
+ "model.layers.25.linear_attn.A_log": "model-00004-of-00004.safetensors",
263
+ "model.layers.25.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
264
+ "model.layers.25.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
265
+ "model.layers.25.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
266
+ "model.layers.25.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
267
+ "model.layers.25.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
268
+ "model.layers.25.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
269
+ "model.layers.25.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
270
+ "model.layers.25.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
271
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
272
+ "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
273
+ "model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
274
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
275
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
276
+ "model.layers.26.linear_attn.A_log": "model-00004-of-00004.safetensors",
277
+ "model.layers.26.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
278
+ "model.layers.26.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
279
+ "model.layers.26.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
280
+ "model.layers.26.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
281
+ "model.layers.26.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
282
+ "model.layers.26.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
283
+ "model.layers.26.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
284
+ "model.layers.26.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
285
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
286
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
287
+ "model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
288
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
289
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
290
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
291
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
292
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
293
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
294
+ "model.layers.27.self_attn.gla.g_norm_swish_gate.weight": "model-00004-of-00004.safetensors",
295
+ "model.layers.27.self_attn.gla.g_proj.weight": "model-00004-of-00004.safetensors",
296
+ "model.layers.27.self_attn.gla.gk_proj.0.weight": "model-00004-of-00004.safetensors",
297
+ "model.layers.27.self_attn.gla.gk_proj.1.bias": "model-00004-of-00004.safetensors",
298
+ "model.layers.27.self_attn.gla.gk_proj.1.weight": "model-00004-of-00004.safetensors",
299
+ "model.layers.27.self_attn.gla.k_proj.weight": "model-00004-of-00004.safetensors",
300
+ "model.layers.27.self_attn.gla.o_proj.weight": "model-00004-of-00004.safetensors",
301
+ "model.layers.27.self_attn.gla.q_proj.weight": "model-00004-of-00004.safetensors",
302
+ "model.layers.27.self_attn.gla.v_proj.weight": "model-00004-of-00004.safetensors",
303
+ "model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
304
+ "model.layers.28.linear_attn.A_log": "model-00004-of-00004.safetensors",
305
+ "model.layers.28.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
306
+ "model.layers.28.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
307
+ "model.layers.28.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
308
+ "model.layers.28.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
309
+ "model.layers.28.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
310
+ "model.layers.28.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
311
+ "model.layers.28.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
312
+ "model.layers.28.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
313
+ "model.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
314
+ "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
315
+ "model.layers.28.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
316
+ "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
317
+ "model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
318
+ "model.layers.29.linear_attn.A_log": "model-00004-of-00004.safetensors",
319
+ "model.layers.29.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
320
+ "model.layers.29.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
321
+ "model.layers.29.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
322
+ "model.layers.29.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
323
+ "model.layers.29.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
324
+ "model.layers.29.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
325
+ "model.layers.29.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
326
+ "model.layers.29.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
327
+ "model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
328
+ "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
329
+ "model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
330
+ "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
331
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
332
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
333
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
334
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
335
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
336
+ "model.layers.3.self_attn.gla.g_norm_swish_gate.weight": "model-00002-of-00004.safetensors",
337
+ "model.layers.3.self_attn.gla.g_proj.weight": "model-00002-of-00004.safetensors",
338
+ "model.layers.3.self_attn.gla.gk_proj.0.weight": "model-00002-of-00004.safetensors",
339
+ "model.layers.3.self_attn.gla.gk_proj.1.bias": "model-00002-of-00004.safetensors",
340
+ "model.layers.3.self_attn.gla.gk_proj.1.weight": "model-00002-of-00004.safetensors",
341
+ "model.layers.3.self_attn.gla.k_proj.weight": "model-00002-of-00004.safetensors",
342
+ "model.layers.3.self_attn.gla.o_proj.weight": "model-00002-of-00004.safetensors",
343
+ "model.layers.3.self_attn.gla.q_proj.weight": "model-00002-of-00004.safetensors",
344
+ "model.layers.3.self_attn.gla.v_proj.weight": "model-00002-of-00004.safetensors",
345
+ "model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
346
+ "model.layers.30.linear_attn.A_log": "model-00004-of-00004.safetensors",
347
+ "model.layers.30.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
348
+ "model.layers.30.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
349
+ "model.layers.30.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
350
+ "model.layers.30.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
351
+ "model.layers.30.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
352
+ "model.layers.30.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
353
+ "model.layers.30.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
354
+ "model.layers.30.linear_attn.out_proj.weight": "model-00004-of-00004.safetensors",
355
+ "model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
356
+ "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
357
+ "model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
358
+ "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
359
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
360
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
361
+ "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
362
+ "model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
363
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
364
+ "model.layers.31.self_attn.gla.g_norm_swish_gate.weight": "model-00004-of-00004.safetensors",
365
+ "model.layers.31.self_attn.gla.g_proj.weight": "model-00004-of-00004.safetensors",
366
+ "model.layers.31.self_attn.gla.gk_proj.0.weight": "model-00004-of-00004.safetensors",
367
+ "model.layers.31.self_attn.gla.gk_proj.1.bias": "model-00004-of-00004.safetensors",
368
+ "model.layers.31.self_attn.gla.gk_proj.1.weight": "model-00004-of-00004.safetensors",
369
+ "model.layers.31.self_attn.gla.k_proj.weight": "model-00004-of-00004.safetensors",
370
+ "model.layers.31.self_attn.gla.o_proj.weight": "model-00004-of-00004.safetensors",
371
+ "model.layers.31.self_attn.gla.q_proj.weight": "model-00004-of-00004.safetensors",
372
+ "model.layers.31.self_attn.gla.v_proj.weight": "model-00004-of-00004.safetensors",
373
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors",
374
+ "model.layers.4.linear_attn.A_log": "model-00002-of-00004.safetensors",
375
+ "model.layers.4.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
376
+ "model.layers.4.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
377
+ "model.layers.4.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
378
+ "model.layers.4.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
379
+ "model.layers.4.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
380
+ "model.layers.4.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
381
+ "model.layers.4.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
382
+ "model.layers.4.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
383
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
384
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
385
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
386
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
387
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
388
+ "model.layers.5.linear_attn.A_log": "model-00002-of-00004.safetensors",
389
+ "model.layers.5.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
390
+ "model.layers.5.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
391
+ "model.layers.5.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
392
+ "model.layers.5.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
393
+ "model.layers.5.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
394
+ "model.layers.5.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
395
+ "model.layers.5.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
396
+ "model.layers.5.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
397
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
398
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
399
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
400
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
401
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
402
+ "model.layers.6.linear_attn.A_log": "model-00002-of-00004.safetensors",
403
+ "model.layers.6.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
404
+ "model.layers.6.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
405
+ "model.layers.6.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
406
+ "model.layers.6.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
407
+ "model.layers.6.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
408
+ "model.layers.6.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
409
+ "model.layers.6.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
410
+ "model.layers.6.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
411
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
412
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
413
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
414
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
415
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
416
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
417
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
418
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
419
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
420
+ "model.layers.7.self_attn.gla.g_norm_swish_gate.weight": "model-00002-of-00004.safetensors",
421
+ "model.layers.7.self_attn.gla.g_proj.weight": "model-00002-of-00004.safetensors",
422
+ "model.layers.7.self_attn.gla.gk_proj.0.weight": "model-00002-of-00004.safetensors",
423
+ "model.layers.7.self_attn.gla.gk_proj.1.bias": "model-00002-of-00004.safetensors",
424
+ "model.layers.7.self_attn.gla.gk_proj.1.weight": "model-00002-of-00004.safetensors",
425
+ "model.layers.7.self_attn.gla.k_proj.weight": "model-00002-of-00004.safetensors",
426
+ "model.layers.7.self_attn.gla.o_proj.weight": "model-00002-of-00004.safetensors",
427
+ "model.layers.7.self_attn.gla.q_proj.weight": "model-00002-of-00004.safetensors",
428
+ "model.layers.7.self_attn.gla.v_proj.weight": "model-00002-of-00004.safetensors",
429
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
430
+ "model.layers.8.linear_attn.A_log": "model-00002-of-00004.safetensors",
431
+ "model.layers.8.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
432
+ "model.layers.8.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
433
+ "model.layers.8.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
434
+ "model.layers.8.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
435
+ "model.layers.8.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
436
+ "model.layers.8.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
437
+ "model.layers.8.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
438
+ "model.layers.8.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
439
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
440
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
441
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
442
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
443
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
444
+ "model.layers.9.linear_attn.A_log": "model-00002-of-00004.safetensors",
445
+ "model.layers.9.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors",
446
+ "model.layers.9.linear_attn.dt_bias": "model-00002-of-00004.safetensors",
447
+ "model.layers.9.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors",
448
+ "model.layers.9.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors",
449
+ "model.layers.9.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors",
450
+ "model.layers.9.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors",
451
+ "model.layers.9.linear_attn.norm.weight": "model-00002-of-00004.safetensors",
452
+ "model.layers.9.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors",
453
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
454
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
455
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
456
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
457
+ "model.norm.weight": "model-00004-of-00004.safetensors"
458
+ }
459
+ }
modeling_qwen3_5.py ADDED
The diff for this file is too large to render. See raw diff