ykhrustalev commited on
Commit
e84d3fc
·
verified ·
1 Parent(s): 5081ed6

Upload folder using huggingface_hub

Browse files
LICENSE ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ LICENSE TEXT
2
+
3
+
4
+
5
+
6
+ LFM Open License v1.0
7
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
8
+ 1. Definitions.
9
+ "License" shall mean the terms and conditions for use, reproduction, and distribution as defined by this document.
10
+ "Licensor" shall mean Liquid AI, Inc.
11
+ "Legal Entity" shall mean the union of the acting entity and all other entities that control, are controlled by, or are under common control with that entity. For the purposes of this definition, "control" means (i) the power, direct or indirect, to cause the direction or management of such entity, whether by contract or otherwise, or (ii) ownership of fifty percent (50%) or more of the outstanding shares, or (iii) beneficial ownership of such entity.
12
+ "You" (or "Your") shall mean an individual or Legal Entity exercising permissions granted by this License.
13
+ "Source" form shall mean the preferred form for making modifications, including but not limited to software source code, documentation source, and configuration files.
14
+ "Object" form shall mean any form resulting from mechanical transformation or translation of a Source form, including but not limited to compiled object code, generated documentation, and conversions to other media types.
15
+ "Work" shall mean the work of authorship, whether in Source or Object form, made available under the License, as indicated by a copyright notice that is included in or attached to the work.
16
+ "Derivative Works" shall mean any work, whether in Source or Object form, that is based on (or derived from) the Work and for which the editorial revisions, annotations, elaborations, or other modifications represent, as a whole, an original work of authorship. For the purposes of this License, Derivative Works shall not include works that remain separable from, or merely link (or bind by name) to the interfaces of, the Work and Derivative Works thereof.
17
+ "Contribution" shall mean any work of authorship, including the original version of the Work and any modifications or additions to that Work or Derivative Works thereof, that is intentionally submitted to Licensor for inclusion in the Work by the copyright owner or by an individual or Legal Entity authorized to submit on behalf of the copyright owner. For the purposes of this definition, "submitted" means any form of electronic, verbal, or written communication sent to the Licensor or its representatives, including but not limited to communication on electronic mailing lists, source code control systems, and issue tracking systems that are managed by, or on behalf of, the Licensor for the purpose of discussing and improving the Work, but excluding communication that is conspicuously marked or otherwise designated in writing by the copyright owner as "Not a Contribution."
18
+ "Contributor" shall mean Licensor and any individual or Legal Entity on behalf of whom a Contribution has been received by Licensor and subsequently incorporated within the Work.
19
+ "Commercial Use" shall mean any use of the Work for direct or indirect commercial advantage or monetary compensation.
20
+ "Qualified Non-Profit Organization" shall mean a Legal Entity that is organized and operated exclusively for religious, charitable, scientific, testing for public safety, literary, or educational purposes, and which is exempt from federal income tax under Section 501(c)(3) of the United States Internal Revenue Code of 1986, as amended, or any equivalent non-profit or charitable organization in a foreign jurisdiction.
21
+ "Non-Commercial or Research Purposes" shall mean purposes that do not involve any use of the Work or a Derivative Work for Commercial Use.
22
+ "Threshold" shall mean annual revenue of 10 million United States dollars ($10,000,000) or more.
23
+ 2. Grant of Copyright License. Subject to the terms and conditions of this License, including the Commercial Use limitation set forth in Section 5, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare Derivative Works of, publicly display, publicly perform, sublicense, and distribute the Work and such Derivative Works in Source or Object form.
24
+ 3. Grant of Patent License. Subject to the terms and conditions of this License, including the Commercial Use limitation set forth in Section 5, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this section) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Work, where such license applies only to those patent claims licensable by such Contributor that are necessarily infringed by their Contribution(s) alone or by combination of their Contribution(s) with the Work to which such Contribution(s) was submitted. If You institute patent litigation against any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Work or a Contribution incorporated within the Work constitutes direct or contributory patent infringement, then any patent licenses granted to You under this License for that Work shall terminate as of the date such litigation is filed.
25
+ 4. Redistribution. You may reproduce and distribute copies of the Work or Derivative Works thereof in any medium, with or without modifications, and in Source or Object form, provided that You meet the following conditions:
26
+ (a) You must give any other recipients of the Work or Derivative Works a copy of this License; and
27
+ (b) You must cause any modified files to carry prominent notices stating that You changed the files; and
28
+ (c) You must retain, in the Source form of any Derivative Works that You distribute, all copyright, patent, trademark, and attribution notices from the Source form of the Work, excluding those notices that do not pertain to any part of the Derivative Works; and
29
+ (d) If the Work includes a "NOTICE" text file as part of its distribution, then any Derivative Works that You distribute must include a readable copy of the attribution notices contained within such NOTICE file, excluding those notices that do not pertain to any part of the Derivative Works, in at least one of the following places: within a NOTICE text file distributed as part of the Derivative Works; within the Source form or documentation, if provided along with the Derivative Works; or, within a display generated by the Derivative Works, if and wherever such third-party notices normally appear. The contents of the NOTICE file are for informational purposes only and do not modify the License. You may add Your own attribution notices within Derivative Works that You distribute, alongside or as an addendum to the NOTICE text from the Work, provided that such additional attribution notices cannot be construed as modifying the License.
30
+ You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of Your modifications, or for any such Derivative Works as a whole, provided Your use, reproduction, and distribution of the Work otherwise complies with the conditions stated in this License.
31
+ 5. Commercial Use Limitation.
32
+ (a) The rights granted under this License for Commercial Use are conditioned upon You or Your Legal Entity not exceeding the Threshold.
33
+ (b) Any Commercial Use of the Work or a Derivative Work by a Legal Entity that exceeds the Threshold is not licensed under this Agreement.
34
+ (c) The Threshold shall not apply to a Qualified Non-Profit Organization's use of the Work or a Derivative Work for Non-Commercial or Research Purposes.
35
+ 6. Submission of Contributions. Unless You explicitly state otherwise, any Contribution intentionally submitted for inclusion in the Work by You to the Licensor shall be under the terms and conditions of this License, without any additional terms or conditions. Notwithstanding the above, nothing herein shall supersede or modify the terms of any separate license agreement you may have executed with Licensor regarding such Contributions.
36
+ 7. Trademarks. This License does not grant permission to use the trade names, trademarks, service marks, or product names of the Licensor, except for the reasonable and customary use in describing the origin of the Work and reproducing the content of the NOTICE file.
37
+ 8. Disclaimer of Warranty. Unless required by applicable law or agreed to in writing, Licensor provides the Work (and each Contributor provides its Contributions) on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely responsible for determining the appropriateness of using or redistributing the Work and assume any risks associated with Your exercise of permissions under this License.
38
+ 9. Limitation of Liability. In no event and under no legal theory, whether in tort (including negligence), contract, or otherwise, unless required by applicable law (such as deliberate and grossly negligent acts) or agreed to in writing, shall any Contributor be liable to You for damages, including any direct, indirect, special, incidental, or consequential damages of any character arising as a result of this License or out of the use or inability to use the Work (including but not limited to damages for loss of goodwill, work stoppage, computer failure or malfunction, or any and all other commercial damages or losses), even if such Contributor has been advised of the possibility of such damages.
39
+ 10. Accepting Warranty or Additional Liability. While redistributing the Work or Derivative Works thereof, You may choose to offer, and charge a fee for, acceptance of support, warranty, indemnity, or other liability obligations and/or rights consistent with this License. However, in accepting such obligations, You may act only on Your own behalf and on Your sole responsibility, not on behalf of any other Contributor, and only if You agree to indemnify, defend, and hold each Contributor harmless for any liability incurred by, or claims asserted against, such Contributor by reason of your accepting any such warranty or additional liability.
40
+ 11. Termination. This License will terminate automatically and immediately if You fail to comply with any of its terms and conditions. Upon termination, You must cease all use of the Work and any Derivative Works and delete all copies in Your possession.
41
+ END OF TERMS AND CONDITIONS
README.md ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: mlx
3
+ license: other
4
+ license_name: lfm1.0
5
+ license_link: LICENSE
6
+ language:
7
+ - en
8
+ pipeline_tag: text-generation
9
+ tags:
10
+ - liquid
11
+ - lfm2
12
+ - moe
13
+ - mlx
14
+ base_model: LiquidAI/LFM2-24B-A2B-Preview
15
+ ---
16
+
17
+ <div align="center">
18
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/2b08LKpev0DNEk6DlnWkY.png" alt="Liquid AI" style="width: 100%; max-width: 100%;">
19
+
20
+ <p>
21
+ <a href="https://playground.liquid.ai/"><strong>Try LFM</strong></a> •
22
+ <a href="https://docs.liquid.ai/lfm"><strong>Documentation</strong></a> •
23
+ <a href="https://leap.liquid.ai/"><strong>LEAP</strong></a> •
24
+ <a href="https://www.liquid.ai/blog/"><strong>Blog</strong></a>
25
+ </p>
26
+ </div>
27
+
28
+ # LFM2-24B-A2B-MLX-8bit
29
+
30
+ MLX export of [LFM2-24B-A2B-Preview](https://huggingface.co/LiquidAI/LFM2-24B-A2B-Preview) for Apple Silicon inference.
31
+
32
+ ## Model Details
33
+
34
+ | Property | Value |
35
+ |----------|-------|
36
+ | Total Parameters | 24B |
37
+ | Active Parameters | ~2B per token |
38
+ | Architecture | Mixture of Experts (64 experts, top-4) |
39
+ | Layers | 40 (30 conv + 10 full attention) |
40
+ | Precision | 8-bit |
41
+ | Group Size | 64 |
42
+ | Size | 23.6 GB |
43
+ | Context Length | 128K |
44
+
45
+ ## Recommended Sampling Parameters
46
+
47
+ | Parameter | Value |
48
+ |-----------|-------|
49
+ | temperature | 0.1 |
50
+ | top_k | 50 |
51
+ | top_p | 0.1 |
52
+ | repetition_penalty | 1.05 |
53
+ | max_tokens | 512 |
54
+
55
+ ## Use with mlx
56
+
57
+ ```bash
58
+ pip install mlx-lm
59
+ ```
60
+
61
+ ```python
62
+ from mlx_lm import load, generate
63
+ from mlx_lm.sample_utils import make_sampler, make_logits_processors
64
+
65
+ model, tokenizer = load("LiquidAI/LFM2-24B-A2B-MLX-8bit")
66
+
67
+ prompt = "What is the capital of France?"
68
+
69
+ if tokenizer.chat_template is not None:
70
+ messages = [{"role": "user", "content": prompt}]
71
+ prompt = tokenizer.apply_chat_template(
72
+ messages, tokenize=False, add_generation_prompt=True
73
+ )
74
+
75
+ sampler = make_sampler(temp=0.1, top_k=50, top_p=0.1)
76
+ logits_processors = make_logits_processors(repetition_penalty=1.05)
77
+
78
+ response = generate(
79
+ model,
80
+ tokenizer,
81
+ prompt=prompt,
82
+ max_tokens=512,
83
+ sampler=sampler,
84
+ logits_processors=logits_processors,
85
+ verbose=True,
86
+ )
87
+ ```
88
+
89
+ ## License
90
+
91
+ This model is released under the [LFM 1.0 License](LICENSE).
chat_template.jinja ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token -}}
2
+ {%- set keep_past_thinking = keep_past_thinking | default(false) -%}
3
+ {%- set ns = namespace(system_prompt="") -%}
4
+ {%- if messages[0]["role"] == "system" -%}
5
+ {%- set sys_content = messages[0]["content"] -%}
6
+ {%- if sys_content is not string -%}
7
+ {%- for item in sys_content -%}
8
+ {%- if item["type"] == "text" -%}
9
+ {%- set ns.system_prompt = ns.system_prompt + item["text"] -%}
10
+ {%- endif -%}
11
+ {%- endfor -%}
12
+ {%- else -%}
13
+ {%- set ns.system_prompt = sys_content -%}
14
+ {%- endif -%}
15
+ {%- set messages = messages[1:] -%}
16
+ {%- endif -%}
17
+ {%- if tools -%}
18
+ {%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: [" -%}
19
+ {%- for tool in tools -%}
20
+ {%- if tool is not string -%}
21
+ {%- set tool = tool | tojson -%}
22
+ {%- endif -%}
23
+ {%- set ns.system_prompt = ns.system_prompt + tool -%}
24
+ {%- if not loop.last -%}
25
+ {%- set ns.system_prompt = ns.system_prompt + ", " -%}
26
+ {%- endif -%}
27
+ {%- endfor -%}
28
+ {%- set ns.system_prompt = ns.system_prompt + "]" -%}
29
+ {%- endif -%}
30
+ {%- if ns.system_prompt -%}
31
+ {{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
32
+ {%- endif -%}
33
+ {%- set ns.last_assistant_index = -1 -%}
34
+ {%- for message in messages -%}
35
+ {%- if message["role"] == "assistant" -%}
36
+ {%- set ns.last_assistant_index = loop.index0 -%}
37
+ {%- endif -%}
38
+ {%- endfor -%}
39
+ {%- for message in messages -%}
40
+ {{- "<|im_start|>" + message["role"] + "\n" -}}
41
+ {%- set content = message["content"] -%}
42
+ {%- if content is not string -%}
43
+ {%- set ns.content = "" -%}
44
+ {%- for item in content -%}
45
+ {%- if item["type"] == "image" -%}
46
+ {%- set ns.content = ns.content + "<image>" -%}
47
+ {%- elif item["type"] == "text" -%}
48
+ {%- set ns.content = ns.content + item["text"] -%}
49
+ {%- else -%}
50
+ {%- set ns.content = ns.content + item | tojson -%}
51
+ {%- endif -%}
52
+ {%- endfor -%}
53
+ {%- set content = ns.content -%}
54
+ {%- endif -%}
55
+ {%- if message["role"] == "assistant" and not keep_past_thinking and loop.index0 != ns.last_assistant_index -%}
56
+ {%- if "</think>" in content -%}
57
+ {%- set content = content.split("</think>")[-1] | trim -%}
58
+ {%- endif -%}
59
+ {%- endif -%}
60
+ {{- content + "<|im_end|>\n" -}}
61
+ {%- endfor -%}
62
+ {%- if add_generation_prompt -%}
63
+ {{- "<|im_start|>assistant\n" -}}
64
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,391 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Lfm2MoeForCausalLM"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "conv_L_cache": 3,
7
+ "conv_bias": false,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 7,
10
+ "hidden_size": 2048,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 11776,
13
+ "layer_types": [
14
+ "conv",
15
+ "conv",
16
+ "full_attention",
17
+ "conv",
18
+ "conv",
19
+ "conv",
20
+ "full_attention",
21
+ "conv",
22
+ "conv",
23
+ "conv",
24
+ "full_attention",
25
+ "conv",
26
+ "conv",
27
+ "conv",
28
+ "full_attention",
29
+ "conv",
30
+ "conv",
31
+ "conv",
32
+ "full_attention",
33
+ "conv",
34
+ "conv",
35
+ "conv",
36
+ "full_attention",
37
+ "conv",
38
+ "conv",
39
+ "conv",
40
+ "full_attention",
41
+ "conv",
42
+ "conv",
43
+ "conv",
44
+ "full_attention",
45
+ "conv",
46
+ "conv",
47
+ "conv",
48
+ "full_attention",
49
+ "conv",
50
+ "conv",
51
+ "conv",
52
+ "full_attention",
53
+ "conv"
54
+ ],
55
+ "max_position_embeddings": 128000,
56
+ "model_type": "lfm2_moe",
57
+ "moe_intermediate_size": 1536,
58
+ "norm_eps": 1e-05,
59
+ "norm_topk_prob": true,
60
+ "num_attention_heads": 32,
61
+ "num_dense_layers": 2,
62
+ "num_experts": 64,
63
+ "num_experts_per_tok": 4,
64
+ "num_hidden_layers": 40,
65
+ "num_key_value_heads": 8,
66
+ "pad_token_id": 0,
67
+ "quantization": {
68
+ "group_size": 64,
69
+ "bits": 8,
70
+ "mode": "affine",
71
+ "model.layers.2.feed_forward.gate": {
72
+ "group_size": 64,
73
+ "bits": 8
74
+ },
75
+ "model.layers.3.feed_forward.gate": {
76
+ "group_size": 64,
77
+ "bits": 8
78
+ },
79
+ "model.layers.4.feed_forward.gate": {
80
+ "group_size": 64,
81
+ "bits": 8
82
+ },
83
+ "model.layers.5.feed_forward.gate": {
84
+ "group_size": 64,
85
+ "bits": 8
86
+ },
87
+ "model.layers.6.feed_forward.gate": {
88
+ "group_size": 64,
89
+ "bits": 8
90
+ },
91
+ "model.layers.7.feed_forward.gate": {
92
+ "group_size": 64,
93
+ "bits": 8
94
+ },
95
+ "model.layers.8.feed_forward.gate": {
96
+ "group_size": 64,
97
+ "bits": 8
98
+ },
99
+ "model.layers.9.feed_forward.gate": {
100
+ "group_size": 64,
101
+ "bits": 8
102
+ },
103
+ "model.layers.10.feed_forward.gate": {
104
+ "group_size": 64,
105
+ "bits": 8
106
+ },
107
+ "model.layers.11.feed_forward.gate": {
108
+ "group_size": 64,
109
+ "bits": 8
110
+ },
111
+ "model.layers.12.feed_forward.gate": {
112
+ "group_size": 64,
113
+ "bits": 8
114
+ },
115
+ "model.layers.13.feed_forward.gate": {
116
+ "group_size": 64,
117
+ "bits": 8
118
+ },
119
+ "model.layers.14.feed_forward.gate": {
120
+ "group_size": 64,
121
+ "bits": 8
122
+ },
123
+ "model.layers.15.feed_forward.gate": {
124
+ "group_size": 64,
125
+ "bits": 8
126
+ },
127
+ "model.layers.16.feed_forward.gate": {
128
+ "group_size": 64,
129
+ "bits": 8
130
+ },
131
+ "model.layers.17.feed_forward.gate": {
132
+ "group_size": 64,
133
+ "bits": 8
134
+ },
135
+ "model.layers.18.feed_forward.gate": {
136
+ "group_size": 64,
137
+ "bits": 8
138
+ },
139
+ "model.layers.19.feed_forward.gate": {
140
+ "group_size": 64,
141
+ "bits": 8
142
+ },
143
+ "model.layers.20.feed_forward.gate": {
144
+ "group_size": 64,
145
+ "bits": 8
146
+ },
147
+ "model.layers.21.feed_forward.gate": {
148
+ "group_size": 64,
149
+ "bits": 8
150
+ },
151
+ "model.layers.22.feed_forward.gate": {
152
+ "group_size": 64,
153
+ "bits": 8
154
+ },
155
+ "model.layers.23.feed_forward.gate": {
156
+ "group_size": 64,
157
+ "bits": 8
158
+ },
159
+ "model.layers.24.feed_forward.gate": {
160
+ "group_size": 64,
161
+ "bits": 8
162
+ },
163
+ "model.layers.25.feed_forward.gate": {
164
+ "group_size": 64,
165
+ "bits": 8
166
+ },
167
+ "model.layers.26.feed_forward.gate": {
168
+ "group_size": 64,
169
+ "bits": 8
170
+ },
171
+ "model.layers.27.feed_forward.gate": {
172
+ "group_size": 64,
173
+ "bits": 8
174
+ },
175
+ "model.layers.28.feed_forward.gate": {
176
+ "group_size": 64,
177
+ "bits": 8
178
+ },
179
+ "model.layers.29.feed_forward.gate": {
180
+ "group_size": 64,
181
+ "bits": 8
182
+ },
183
+ "model.layers.30.feed_forward.gate": {
184
+ "group_size": 64,
185
+ "bits": 8
186
+ },
187
+ "model.layers.31.feed_forward.gate": {
188
+ "group_size": 64,
189
+ "bits": 8
190
+ },
191
+ "model.layers.32.feed_forward.gate": {
192
+ "group_size": 64,
193
+ "bits": 8
194
+ },
195
+ "model.layers.33.feed_forward.gate": {
196
+ "group_size": 64,
197
+ "bits": 8
198
+ },
199
+ "model.layers.34.feed_forward.gate": {
200
+ "group_size": 64,
201
+ "bits": 8
202
+ },
203
+ "model.layers.35.feed_forward.gate": {
204
+ "group_size": 64,
205
+ "bits": 8
206
+ },
207
+ "model.layers.36.feed_forward.gate": {
208
+ "group_size": 64,
209
+ "bits": 8
210
+ },
211
+ "model.layers.37.feed_forward.gate": {
212
+ "group_size": 64,
213
+ "bits": 8
214
+ },
215
+ "model.layers.38.feed_forward.gate": {
216
+ "group_size": 64,
217
+ "bits": 8
218
+ },
219
+ "model.layers.39.feed_forward.gate": {
220
+ "group_size": 64,
221
+ "bits": 8
222
+ }
223
+ },
224
+ "quantization_config": {
225
+ "group_size": 64,
226
+ "bits": 8,
227
+ "mode": "affine",
228
+ "model.layers.2.feed_forward.gate": {
229
+ "group_size": 64,
230
+ "bits": 8
231
+ },
232
+ "model.layers.3.feed_forward.gate": {
233
+ "group_size": 64,
234
+ "bits": 8
235
+ },
236
+ "model.layers.4.feed_forward.gate": {
237
+ "group_size": 64,
238
+ "bits": 8
239
+ },
240
+ "model.layers.5.feed_forward.gate": {
241
+ "group_size": 64,
242
+ "bits": 8
243
+ },
244
+ "model.layers.6.feed_forward.gate": {
245
+ "group_size": 64,
246
+ "bits": 8
247
+ },
248
+ "model.layers.7.feed_forward.gate": {
249
+ "group_size": 64,
250
+ "bits": 8
251
+ },
252
+ "model.layers.8.feed_forward.gate": {
253
+ "group_size": 64,
254
+ "bits": 8
255
+ },
256
+ "model.layers.9.feed_forward.gate": {
257
+ "group_size": 64,
258
+ "bits": 8
259
+ },
260
+ "model.layers.10.feed_forward.gate": {
261
+ "group_size": 64,
262
+ "bits": 8
263
+ },
264
+ "model.layers.11.feed_forward.gate": {
265
+ "group_size": 64,
266
+ "bits": 8
267
+ },
268
+ "model.layers.12.feed_forward.gate": {
269
+ "group_size": 64,
270
+ "bits": 8
271
+ },
272
+ "model.layers.13.feed_forward.gate": {
273
+ "group_size": 64,
274
+ "bits": 8
275
+ },
276
+ "model.layers.14.feed_forward.gate": {
277
+ "group_size": 64,
278
+ "bits": 8
279
+ },
280
+ "model.layers.15.feed_forward.gate": {
281
+ "group_size": 64,
282
+ "bits": 8
283
+ },
284
+ "model.layers.16.feed_forward.gate": {
285
+ "group_size": 64,
286
+ "bits": 8
287
+ },
288
+ "model.layers.17.feed_forward.gate": {
289
+ "group_size": 64,
290
+ "bits": 8
291
+ },
292
+ "model.layers.18.feed_forward.gate": {
293
+ "group_size": 64,
294
+ "bits": 8
295
+ },
296
+ "model.layers.19.feed_forward.gate": {
297
+ "group_size": 64,
298
+ "bits": 8
299
+ },
300
+ "model.layers.20.feed_forward.gate": {
301
+ "group_size": 64,
302
+ "bits": 8
303
+ },
304
+ "model.layers.21.feed_forward.gate": {
305
+ "group_size": 64,
306
+ "bits": 8
307
+ },
308
+ "model.layers.22.feed_forward.gate": {
309
+ "group_size": 64,
310
+ "bits": 8
311
+ },
312
+ "model.layers.23.feed_forward.gate": {
313
+ "group_size": 64,
314
+ "bits": 8
315
+ },
316
+ "model.layers.24.feed_forward.gate": {
317
+ "group_size": 64,
318
+ "bits": 8
319
+ },
320
+ "model.layers.25.feed_forward.gate": {
321
+ "group_size": 64,
322
+ "bits": 8
323
+ },
324
+ "model.layers.26.feed_forward.gate": {
325
+ "group_size": 64,
326
+ "bits": 8
327
+ },
328
+ "model.layers.27.feed_forward.gate": {
329
+ "group_size": 64,
330
+ "bits": 8
331
+ },
332
+ "model.layers.28.feed_forward.gate": {
333
+ "group_size": 64,
334
+ "bits": 8
335
+ },
336
+ "model.layers.29.feed_forward.gate": {
337
+ "group_size": 64,
338
+ "bits": 8
339
+ },
340
+ "model.layers.30.feed_forward.gate": {
341
+ "group_size": 64,
342
+ "bits": 8
343
+ },
344
+ "model.layers.31.feed_forward.gate": {
345
+ "group_size": 64,
346
+ "bits": 8
347
+ },
348
+ "model.layers.32.feed_forward.gate": {
349
+ "group_size": 64,
350
+ "bits": 8
351
+ },
352
+ "model.layers.33.feed_forward.gate": {
353
+ "group_size": 64,
354
+ "bits": 8
355
+ },
356
+ "model.layers.34.feed_forward.gate": {
357
+ "group_size": 64,
358
+ "bits": 8
359
+ },
360
+ "model.layers.35.feed_forward.gate": {
361
+ "group_size": 64,
362
+ "bits": 8
363
+ },
364
+ "model.layers.36.feed_forward.gate": {
365
+ "group_size": 64,
366
+ "bits": 8
367
+ },
368
+ "model.layers.37.feed_forward.gate": {
369
+ "group_size": 64,
370
+ "bits": 8
371
+ },
372
+ "model.layers.38.feed_forward.gate": {
373
+ "group_size": 64,
374
+ "bits": 8
375
+ },
376
+ "model.layers.39.feed_forward.gate": {
377
+ "group_size": 64,
378
+ "bits": 8
379
+ }
380
+ },
381
+ "rope_parameters": {
382
+ "rope_theta": 1000000.0,
383
+ "rope_type": "default"
384
+ },
385
+ "rope_theta": 1000000.0,
386
+ "routed_scaling_factor": 1.0,
387
+ "transformers_version": "5.0.0rc1",
388
+ "use_cache": true,
389
+ "use_expert_bias": true,
390
+ "vocab_size": 65536
391
+ }
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7324a52504574de050630f691d4c92ab7d7619cb4a3c5ab685070952e2211d1
3
+ size 5168566118
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fafcbe86aa3d52ec72f5bd82026ff191b1ebfff966129082c9d436da22eec2e
3
+ size 5264344037
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24149d664fae83f38e94ddcf5ae117e476f10681d377dfe188c7e64666929423
3
+ size 5264343998
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:198186f5e3e74f2134b80ebd5ef7c93951dc4491acd2297c4d132b98e374fc5e
3
+ size 5264344074
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb658f5f945ac8d54620090d4d66da628007702b727299eae9d8bba88342857b
3
+ size 4372742875
model.safetensors.index.json ADDED
@@ -0,0 +1,954 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 25334226944,
4
+ "total_parameters": 23843659008
5
+ },
6
+ "weight_map": {
7
+ "model.embed_tokens.biases": "model-00001-of-00005.safetensors",
8
+ "model.embed_tokens.scales": "model-00001-of-00005.safetensors",
9
+ "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
10
+ "model.embedding_norm.weight": "model-00005-of-00005.safetensors",
11
+ "model.layers.0.conv.conv.weight": "model-00001-of-00005.safetensors",
12
+ "model.layers.0.conv.in_proj.biases": "model-00001-of-00005.safetensors",
13
+ "model.layers.0.conv.in_proj.scales": "model-00001-of-00005.safetensors",
14
+ "model.layers.0.conv.in_proj.weight": "model-00001-of-00005.safetensors",
15
+ "model.layers.0.conv.out_proj.biases": "model-00001-of-00005.safetensors",
16
+ "model.layers.0.conv.out_proj.scales": "model-00001-of-00005.safetensors",
17
+ "model.layers.0.conv.out_proj.weight": "model-00001-of-00005.safetensors",
18
+ "model.layers.0.feed_forward.down_proj.biases": "model-00001-of-00005.safetensors",
19
+ "model.layers.0.feed_forward.down_proj.scales": "model-00001-of-00005.safetensors",
20
+ "model.layers.0.feed_forward.down_proj.weight": "model-00001-of-00005.safetensors",
21
+ "model.layers.0.feed_forward.gate_proj.biases": "model-00001-of-00005.safetensors",
22
+ "model.layers.0.feed_forward.gate_proj.scales": "model-00001-of-00005.safetensors",
23
+ "model.layers.0.feed_forward.gate_proj.weight": "model-00001-of-00005.safetensors",
24
+ "model.layers.0.feed_forward.up_proj.biases": "model-00001-of-00005.safetensors",
25
+ "model.layers.0.feed_forward.up_proj.scales": "model-00001-of-00005.safetensors",
26
+ "model.layers.0.feed_forward.up_proj.weight": "model-00001-of-00005.safetensors",
27
+ "model.layers.0.ffn_norm.weight": "model-00001-of-00005.safetensors",
28
+ "model.layers.0.operator_norm.weight": "model-00001-of-00005.safetensors",
29
+ "model.layers.1.conv.conv.weight": "model-00001-of-00005.safetensors",
30
+ "model.layers.1.conv.in_proj.biases": "model-00001-of-00005.safetensors",
31
+ "model.layers.1.conv.in_proj.scales": "model-00001-of-00005.safetensors",
32
+ "model.layers.1.conv.in_proj.weight": "model-00001-of-00005.safetensors",
33
+ "model.layers.1.conv.out_proj.biases": "model-00001-of-00005.safetensors",
34
+ "model.layers.1.conv.out_proj.scales": "model-00001-of-00005.safetensors",
35
+ "model.layers.1.conv.out_proj.weight": "model-00001-of-00005.safetensors",
36
+ "model.layers.1.feed_forward.down_proj.biases": "model-00001-of-00005.safetensors",
37
+ "model.layers.1.feed_forward.down_proj.scales": "model-00001-of-00005.safetensors",
38
+ "model.layers.1.feed_forward.down_proj.weight": "model-00001-of-00005.safetensors",
39
+ "model.layers.1.feed_forward.gate_proj.biases": "model-00001-of-00005.safetensors",
40
+ "model.layers.1.feed_forward.gate_proj.scales": "model-00001-of-00005.safetensors",
41
+ "model.layers.1.feed_forward.gate_proj.weight": "model-00001-of-00005.safetensors",
42
+ "model.layers.1.feed_forward.up_proj.biases": "model-00001-of-00005.safetensors",
43
+ "model.layers.1.feed_forward.up_proj.scales": "model-00001-of-00005.safetensors",
44
+ "model.layers.1.feed_forward.up_proj.weight": "model-00001-of-00005.safetensors",
45
+ "model.layers.1.ffn_norm.weight": "model-00001-of-00005.safetensors",
46
+ "model.layers.1.operator_norm.weight": "model-00001-of-00005.safetensors",
47
+ "model.layers.10.feed_forward.expert_bias": "model-00002-of-00005.safetensors",
48
+ "model.layers.10.feed_forward.gate.biases": "model-00002-of-00005.safetensors",
49
+ "model.layers.10.feed_forward.gate.scales": "model-00002-of-00005.safetensors",
50
+ "model.layers.10.feed_forward.gate.weight": "model-00002-of-00005.safetensors",
51
+ "model.layers.10.feed_forward.switch_mlp.down_proj.biases": "model-00002-of-00005.safetensors",
52
+ "model.layers.10.feed_forward.switch_mlp.down_proj.scales": "model-00002-of-00005.safetensors",
53
+ "model.layers.10.feed_forward.switch_mlp.down_proj.weight": "model-00002-of-00005.safetensors",
54
+ "model.layers.10.feed_forward.switch_mlp.gate_proj.biases": "model-00002-of-00005.safetensors",
55
+ "model.layers.10.feed_forward.switch_mlp.gate_proj.scales": "model-00002-of-00005.safetensors",
56
+ "model.layers.10.feed_forward.switch_mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
57
+ "model.layers.10.feed_forward.switch_mlp.up_proj.biases": "model-00002-of-00005.safetensors",
58
+ "model.layers.10.feed_forward.switch_mlp.up_proj.scales": "model-00002-of-00005.safetensors",
59
+ "model.layers.10.feed_forward.switch_mlp.up_proj.weight": "model-00002-of-00005.safetensors",
60
+ "model.layers.10.ffn_norm.weight": "model-00002-of-00005.safetensors",
61
+ "model.layers.10.operator_norm.weight": "model-00002-of-00005.safetensors",
62
+ "model.layers.10.self_attn.k_layernorm.weight": "model-00002-of-00005.safetensors",
63
+ "model.layers.10.self_attn.k_proj.biases": "model-00002-of-00005.safetensors",
64
+ "model.layers.10.self_attn.k_proj.scales": "model-00002-of-00005.safetensors",
65
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
66
+ "model.layers.10.self_attn.out_proj.biases": "model-00002-of-00005.safetensors",
67
+ "model.layers.10.self_attn.out_proj.scales": "model-00002-of-00005.safetensors",
68
+ "model.layers.10.self_attn.out_proj.weight": "model-00002-of-00005.safetensors",
69
+ "model.layers.10.self_attn.q_layernorm.weight": "model-00002-of-00005.safetensors",
70
+ "model.layers.10.self_attn.q_proj.biases": "model-00002-of-00005.safetensors",
71
+ "model.layers.10.self_attn.q_proj.scales": "model-00002-of-00005.safetensors",
72
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
73
+ "model.layers.10.self_attn.v_proj.biases": "model-00002-of-00005.safetensors",
74
+ "model.layers.10.self_attn.v_proj.scales": "model-00002-of-00005.safetensors",
75
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
76
+ "model.layers.11.conv.conv.weight": "model-00002-of-00005.safetensors",
77
+ "model.layers.11.conv.in_proj.biases": "model-00002-of-00005.safetensors",
78
+ "model.layers.11.conv.in_proj.scales": "model-00002-of-00005.safetensors",
79
+ "model.layers.11.conv.in_proj.weight": "model-00002-of-00005.safetensors",
80
+ "model.layers.11.conv.out_proj.biases": "model-00002-of-00005.safetensors",
81
+ "model.layers.11.conv.out_proj.scales": "model-00002-of-00005.safetensors",
82
+ "model.layers.11.conv.out_proj.weight": "model-00002-of-00005.safetensors",
83
+ "model.layers.11.feed_forward.expert_bias": "model-00002-of-00005.safetensors",
84
+ "model.layers.11.feed_forward.gate.biases": "model-00002-of-00005.safetensors",
85
+ "model.layers.11.feed_forward.gate.scales": "model-00002-of-00005.safetensors",
86
+ "model.layers.11.feed_forward.gate.weight": "model-00002-of-00005.safetensors",
87
+ "model.layers.11.feed_forward.switch_mlp.down_proj.biases": "model-00002-of-00005.safetensors",
88
+ "model.layers.11.feed_forward.switch_mlp.down_proj.scales": "model-00002-of-00005.safetensors",
89
+ "model.layers.11.feed_forward.switch_mlp.down_proj.weight": "model-00002-of-00005.safetensors",
90
+ "model.layers.11.feed_forward.switch_mlp.gate_proj.biases": "model-00002-of-00005.safetensors",
91
+ "model.layers.11.feed_forward.switch_mlp.gate_proj.scales": "model-00002-of-00005.safetensors",
92
+ "model.layers.11.feed_forward.switch_mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
93
+ "model.layers.11.feed_forward.switch_mlp.up_proj.biases": "model-00002-of-00005.safetensors",
94
+ "model.layers.11.feed_forward.switch_mlp.up_proj.scales": "model-00002-of-00005.safetensors",
95
+ "model.layers.11.feed_forward.switch_mlp.up_proj.weight": "model-00002-of-00005.safetensors",
96
+ "model.layers.11.ffn_norm.weight": "model-00002-of-00005.safetensors",
97
+ "model.layers.11.operator_norm.weight": "model-00002-of-00005.safetensors",
98
+ "model.layers.12.conv.conv.weight": "model-00002-of-00005.safetensors",
99
+ "model.layers.12.conv.in_proj.biases": "model-00002-of-00005.safetensors",
100
+ "model.layers.12.conv.in_proj.scales": "model-00002-of-00005.safetensors",
101
+ "model.layers.12.conv.in_proj.weight": "model-00002-of-00005.safetensors",
102
+ "model.layers.12.conv.out_proj.biases": "model-00002-of-00005.safetensors",
103
+ "model.layers.12.conv.out_proj.scales": "model-00002-of-00005.safetensors",
104
+ "model.layers.12.conv.out_proj.weight": "model-00002-of-00005.safetensors",
105
+ "model.layers.12.feed_forward.expert_bias": "model-00002-of-00005.safetensors",
106
+ "model.layers.12.feed_forward.gate.biases": "model-00002-of-00005.safetensors",
107
+ "model.layers.12.feed_forward.gate.scales": "model-00002-of-00005.safetensors",
108
+ "model.layers.12.feed_forward.gate.weight": "model-00002-of-00005.safetensors",
109
+ "model.layers.12.feed_forward.switch_mlp.down_proj.biases": "model-00002-of-00005.safetensors",
110
+ "model.layers.12.feed_forward.switch_mlp.down_proj.scales": "model-00002-of-00005.safetensors",
111
+ "model.layers.12.feed_forward.switch_mlp.down_proj.weight": "model-00002-of-00005.safetensors",
112
+ "model.layers.12.feed_forward.switch_mlp.gate_proj.biases": "model-00002-of-00005.safetensors",
113
+ "model.layers.12.feed_forward.switch_mlp.gate_proj.scales": "model-00002-of-00005.safetensors",
114
+ "model.layers.12.feed_forward.switch_mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
115
+ "model.layers.12.feed_forward.switch_mlp.up_proj.biases": "model-00002-of-00005.safetensors",
116
+ "model.layers.12.feed_forward.switch_mlp.up_proj.scales": "model-00002-of-00005.safetensors",
117
+ "model.layers.12.feed_forward.switch_mlp.up_proj.weight": "model-00002-of-00005.safetensors",
118
+ "model.layers.12.ffn_norm.weight": "model-00002-of-00005.safetensors",
119
+ "model.layers.12.operator_norm.weight": "model-00002-of-00005.safetensors",
120
+ "model.layers.13.conv.conv.weight": "model-00002-of-00005.safetensors",
121
+ "model.layers.13.conv.in_proj.biases": "model-00002-of-00005.safetensors",
122
+ "model.layers.13.conv.in_proj.scales": "model-00002-of-00005.safetensors",
123
+ "model.layers.13.conv.in_proj.weight": "model-00002-of-00005.safetensors",
124
+ "model.layers.13.conv.out_proj.biases": "model-00002-of-00005.safetensors",
125
+ "model.layers.13.conv.out_proj.scales": "model-00002-of-00005.safetensors",
126
+ "model.layers.13.conv.out_proj.weight": "model-00002-of-00005.safetensors",
127
+ "model.layers.13.feed_forward.expert_bias": "model-00002-of-00005.safetensors",
128
+ "model.layers.13.feed_forward.gate.biases": "model-00002-of-00005.safetensors",
129
+ "model.layers.13.feed_forward.gate.scales": "model-00002-of-00005.safetensors",
130
+ "model.layers.13.feed_forward.gate.weight": "model-00002-of-00005.safetensors",
131
+ "model.layers.13.feed_forward.switch_mlp.down_proj.biases": "model-00002-of-00005.safetensors",
132
+ "model.layers.13.feed_forward.switch_mlp.down_proj.scales": "model-00002-of-00005.safetensors",
133
+ "model.layers.13.feed_forward.switch_mlp.down_proj.weight": "model-00002-of-00005.safetensors",
134
+ "model.layers.13.feed_forward.switch_mlp.gate_proj.biases": "model-00002-of-00005.safetensors",
135
+ "model.layers.13.feed_forward.switch_mlp.gate_proj.scales": "model-00002-of-00005.safetensors",
136
+ "model.layers.13.feed_forward.switch_mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
137
+ "model.layers.13.feed_forward.switch_mlp.up_proj.biases": "model-00002-of-00005.safetensors",
138
+ "model.layers.13.feed_forward.switch_mlp.up_proj.scales": "model-00002-of-00005.safetensors",
139
+ "model.layers.13.feed_forward.switch_mlp.up_proj.weight": "model-00002-of-00005.safetensors",
140
+ "model.layers.13.ffn_norm.weight": "model-00002-of-00005.safetensors",
141
+ "model.layers.13.operator_norm.weight": "model-00002-of-00005.safetensors",
142
+ "model.layers.14.feed_forward.expert_bias": "model-00002-of-00005.safetensors",
143
+ "model.layers.14.feed_forward.gate.biases": "model-00002-of-00005.safetensors",
144
+ "model.layers.14.feed_forward.gate.scales": "model-00002-of-00005.safetensors",
145
+ "model.layers.14.feed_forward.gate.weight": "model-00002-of-00005.safetensors",
146
+ "model.layers.14.feed_forward.switch_mlp.down_proj.biases": "model-00002-of-00005.safetensors",
147
+ "model.layers.14.feed_forward.switch_mlp.down_proj.scales": "model-00002-of-00005.safetensors",
148
+ "model.layers.14.feed_forward.switch_mlp.down_proj.weight": "model-00002-of-00005.safetensors",
149
+ "model.layers.14.feed_forward.switch_mlp.gate_proj.biases": "model-00002-of-00005.safetensors",
150
+ "model.layers.14.feed_forward.switch_mlp.gate_proj.scales": "model-00002-of-00005.safetensors",
151
+ "model.layers.14.feed_forward.switch_mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
152
+ "model.layers.14.feed_forward.switch_mlp.up_proj.biases": "model-00002-of-00005.safetensors",
153
+ "model.layers.14.feed_forward.switch_mlp.up_proj.scales": "model-00002-of-00005.safetensors",
154
+ "model.layers.14.feed_forward.switch_mlp.up_proj.weight": "model-00002-of-00005.safetensors",
155
+ "model.layers.14.ffn_norm.weight": "model-00002-of-00005.safetensors",
156
+ "model.layers.14.operator_norm.weight": "model-00002-of-00005.safetensors",
157
+ "model.layers.14.self_attn.k_layernorm.weight": "model-00002-of-00005.safetensors",
158
+ "model.layers.14.self_attn.k_proj.biases": "model-00002-of-00005.safetensors",
159
+ "model.layers.14.self_attn.k_proj.scales": "model-00002-of-00005.safetensors",
160
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
161
+ "model.layers.14.self_attn.out_proj.biases": "model-00002-of-00005.safetensors",
162
+ "model.layers.14.self_attn.out_proj.scales": "model-00002-of-00005.safetensors",
163
+ "model.layers.14.self_attn.out_proj.weight": "model-00002-of-00005.safetensors",
164
+ "model.layers.14.self_attn.q_layernorm.weight": "model-00002-of-00005.safetensors",
165
+ "model.layers.14.self_attn.q_proj.biases": "model-00002-of-00005.safetensors",
166
+ "model.layers.14.self_attn.q_proj.scales": "model-00002-of-00005.safetensors",
167
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
168
+ "model.layers.14.self_attn.v_proj.biases": "model-00002-of-00005.safetensors",
169
+ "model.layers.14.self_attn.v_proj.scales": "model-00002-of-00005.safetensors",
170
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
171
+ "model.layers.15.conv.conv.weight": "model-00002-of-00005.safetensors",
172
+ "model.layers.15.conv.in_proj.biases": "model-00002-of-00005.safetensors",
173
+ "model.layers.15.conv.in_proj.scales": "model-00002-of-00005.safetensors",
174
+ "model.layers.15.conv.in_proj.weight": "model-00002-of-00005.safetensors",
175
+ "model.layers.15.conv.out_proj.biases": "model-00002-of-00005.safetensors",
176
+ "model.layers.15.conv.out_proj.scales": "model-00002-of-00005.safetensors",
177
+ "model.layers.15.conv.out_proj.weight": "model-00002-of-00005.safetensors",
178
+ "model.layers.15.feed_forward.expert_bias": "model-00002-of-00005.safetensors",
179
+ "model.layers.15.feed_forward.gate.biases": "model-00002-of-00005.safetensors",
180
+ "model.layers.15.feed_forward.gate.scales": "model-00002-of-00005.safetensors",
181
+ "model.layers.15.feed_forward.gate.weight": "model-00002-of-00005.safetensors",
182
+ "model.layers.15.feed_forward.switch_mlp.down_proj.biases": "model-00002-of-00005.safetensors",
183
+ "model.layers.15.feed_forward.switch_mlp.down_proj.scales": "model-00002-of-00005.safetensors",
184
+ "model.layers.15.feed_forward.switch_mlp.down_proj.weight": "model-00002-of-00005.safetensors",
185
+ "model.layers.15.feed_forward.switch_mlp.gate_proj.biases": "model-00002-of-00005.safetensors",
186
+ "model.layers.15.feed_forward.switch_mlp.gate_proj.scales": "model-00002-of-00005.safetensors",
187
+ "model.layers.15.feed_forward.switch_mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
188
+ "model.layers.15.feed_forward.switch_mlp.up_proj.biases": "model-00002-of-00005.safetensors",
189
+ "model.layers.15.feed_forward.switch_mlp.up_proj.scales": "model-00002-of-00005.safetensors",
190
+ "model.layers.15.feed_forward.switch_mlp.up_proj.weight": "model-00002-of-00005.safetensors",
191
+ "model.layers.15.ffn_norm.weight": "model-00002-of-00005.safetensors",
192
+ "model.layers.15.operator_norm.weight": "model-00002-of-00005.safetensors",
193
+ "model.layers.16.conv.conv.weight": "model-00002-of-00005.safetensors",
194
+ "model.layers.16.conv.in_proj.biases": "model-00002-of-00005.safetensors",
195
+ "model.layers.16.conv.in_proj.scales": "model-00002-of-00005.safetensors",
196
+ "model.layers.16.conv.in_proj.weight": "model-00002-of-00005.safetensors",
197
+ "model.layers.16.conv.out_proj.biases": "model-00002-of-00005.safetensors",
198
+ "model.layers.16.conv.out_proj.scales": "model-00002-of-00005.safetensors",
199
+ "model.layers.16.conv.out_proj.weight": "model-00002-of-00005.safetensors",
200
+ "model.layers.16.feed_forward.expert_bias": "model-00002-of-00005.safetensors",
201
+ "model.layers.16.feed_forward.gate.biases": "model-00002-of-00005.safetensors",
202
+ "model.layers.16.feed_forward.gate.scales": "model-00002-of-00005.safetensors",
203
+ "model.layers.16.feed_forward.gate.weight": "model-00002-of-00005.safetensors",
204
+ "model.layers.16.feed_forward.switch_mlp.down_proj.biases": "model-00002-of-00005.safetensors",
205
+ "model.layers.16.feed_forward.switch_mlp.down_proj.scales": "model-00002-of-00005.safetensors",
206
+ "model.layers.16.feed_forward.switch_mlp.down_proj.weight": "model-00002-of-00005.safetensors",
207
+ "model.layers.16.feed_forward.switch_mlp.gate_proj.biases": "model-00002-of-00005.safetensors",
208
+ "model.layers.16.feed_forward.switch_mlp.gate_proj.scales": "model-00002-of-00005.safetensors",
209
+ "model.layers.16.feed_forward.switch_mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
210
+ "model.layers.16.feed_forward.switch_mlp.up_proj.biases": "model-00002-of-00005.safetensors",
211
+ "model.layers.16.feed_forward.switch_mlp.up_proj.scales": "model-00002-of-00005.safetensors",
212
+ "model.layers.16.feed_forward.switch_mlp.up_proj.weight": "model-00002-of-00005.safetensors",
213
+ "model.layers.16.ffn_norm.weight": "model-00002-of-00005.safetensors",
214
+ "model.layers.16.operator_norm.weight": "model-00002-of-00005.safetensors",
215
+ "model.layers.17.conv.conv.weight": "model-00002-of-00005.safetensors",
216
+ "model.layers.17.conv.in_proj.biases": "model-00002-of-00005.safetensors",
217
+ "model.layers.17.conv.in_proj.scales": "model-00002-of-00005.safetensors",
218
+ "model.layers.17.conv.in_proj.weight": "model-00002-of-00005.safetensors",
219
+ "model.layers.17.conv.out_proj.biases": "model-00002-of-00005.safetensors",
220
+ "model.layers.17.conv.out_proj.scales": "model-00002-of-00005.safetensors",
221
+ "model.layers.17.conv.out_proj.weight": "model-00002-of-00005.safetensors",
222
+ "model.layers.17.feed_forward.expert_bias": "model-00003-of-00005.safetensors",
223
+ "model.layers.17.feed_forward.gate.biases": "model-00002-of-00005.safetensors",
224
+ "model.layers.17.feed_forward.gate.scales": "model-00002-of-00005.safetensors",
225
+ "model.layers.17.feed_forward.gate.weight": "model-00002-of-00005.safetensors",
226
+ "model.layers.17.feed_forward.switch_mlp.down_proj.biases": "model-00003-of-00005.safetensors",
227
+ "model.layers.17.feed_forward.switch_mlp.down_proj.scales": "model-00003-of-00005.safetensors",
228
+ "model.layers.17.feed_forward.switch_mlp.down_proj.weight": "model-00003-of-00005.safetensors",
229
+ "model.layers.17.feed_forward.switch_mlp.gate_proj.biases": "model-00002-of-00005.safetensors",
230
+ "model.layers.17.feed_forward.switch_mlp.gate_proj.scales": "model-00002-of-00005.safetensors",
231
+ "model.layers.17.feed_forward.switch_mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
232
+ "model.layers.17.feed_forward.switch_mlp.up_proj.biases": "model-00003-of-00005.safetensors",
233
+ "model.layers.17.feed_forward.switch_mlp.up_proj.scales": "model-00003-of-00005.safetensors",
234
+ "model.layers.17.feed_forward.switch_mlp.up_proj.weight": "model-00003-of-00005.safetensors",
235
+ "model.layers.17.ffn_norm.weight": "model-00003-of-00005.safetensors",
236
+ "model.layers.17.operator_norm.weight": "model-00003-of-00005.safetensors",
237
+ "model.layers.18.feed_forward.expert_bias": "model-00003-of-00005.safetensors",
238
+ "model.layers.18.feed_forward.gate.biases": "model-00003-of-00005.safetensors",
239
+ "model.layers.18.feed_forward.gate.scales": "model-00003-of-00005.safetensors",
240
+ "model.layers.18.feed_forward.gate.weight": "model-00003-of-00005.safetensors",
241
+ "model.layers.18.feed_forward.switch_mlp.down_proj.biases": "model-00003-of-00005.safetensors",
242
+ "model.layers.18.feed_forward.switch_mlp.down_proj.scales": "model-00003-of-00005.safetensors",
243
+ "model.layers.18.feed_forward.switch_mlp.down_proj.weight": "model-00003-of-00005.safetensors",
244
+ "model.layers.18.feed_forward.switch_mlp.gate_proj.biases": "model-00003-of-00005.safetensors",
245
+ "model.layers.18.feed_forward.switch_mlp.gate_proj.scales": "model-00003-of-00005.safetensors",
246
+ "model.layers.18.feed_forward.switch_mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
247
+ "model.layers.18.feed_forward.switch_mlp.up_proj.biases": "model-00003-of-00005.safetensors",
248
+ "model.layers.18.feed_forward.switch_mlp.up_proj.scales": "model-00003-of-00005.safetensors",
249
+ "model.layers.18.feed_forward.switch_mlp.up_proj.weight": "model-00003-of-00005.safetensors",
250
+ "model.layers.18.ffn_norm.weight": "model-00003-of-00005.safetensors",
251
+ "model.layers.18.operator_norm.weight": "model-00003-of-00005.safetensors",
252
+ "model.layers.18.self_attn.k_layernorm.weight": "model-00003-of-00005.safetensors",
253
+ "model.layers.18.self_attn.k_proj.biases": "model-00003-of-00005.safetensors",
254
+ "model.layers.18.self_attn.k_proj.scales": "model-00003-of-00005.safetensors",
255
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
256
+ "model.layers.18.self_attn.out_proj.biases": "model-00003-of-00005.safetensors",
257
+ "model.layers.18.self_attn.out_proj.scales": "model-00003-of-00005.safetensors",
258
+ "model.layers.18.self_attn.out_proj.weight": "model-00003-of-00005.safetensors",
259
+ "model.layers.18.self_attn.q_layernorm.weight": "model-00003-of-00005.safetensors",
260
+ "model.layers.18.self_attn.q_proj.biases": "model-00003-of-00005.safetensors",
261
+ "model.layers.18.self_attn.q_proj.scales": "model-00003-of-00005.safetensors",
262
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
263
+ "model.layers.18.self_attn.v_proj.biases": "model-00003-of-00005.safetensors",
264
+ "model.layers.18.self_attn.v_proj.scales": "model-00003-of-00005.safetensors",
265
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
266
+ "model.layers.19.conv.conv.weight": "model-00003-of-00005.safetensors",
267
+ "model.layers.19.conv.in_proj.biases": "model-00003-of-00005.safetensors",
268
+ "model.layers.19.conv.in_proj.scales": "model-00003-of-00005.safetensors",
269
+ "model.layers.19.conv.in_proj.weight": "model-00003-of-00005.safetensors",
270
+ "model.layers.19.conv.out_proj.biases": "model-00003-of-00005.safetensors",
271
+ "model.layers.19.conv.out_proj.scales": "model-00003-of-00005.safetensors",
272
+ "model.layers.19.conv.out_proj.weight": "model-00003-of-00005.safetensors",
273
+ "model.layers.19.feed_forward.expert_bias": "model-00003-of-00005.safetensors",
274
+ "model.layers.19.feed_forward.gate.biases": "model-00003-of-00005.safetensors",
275
+ "model.layers.19.feed_forward.gate.scales": "model-00003-of-00005.safetensors",
276
+ "model.layers.19.feed_forward.gate.weight": "model-00003-of-00005.safetensors",
277
+ "model.layers.19.feed_forward.switch_mlp.down_proj.biases": "model-00003-of-00005.safetensors",
278
+ "model.layers.19.feed_forward.switch_mlp.down_proj.scales": "model-00003-of-00005.safetensors",
279
+ "model.layers.19.feed_forward.switch_mlp.down_proj.weight": "model-00003-of-00005.safetensors",
280
+ "model.layers.19.feed_forward.switch_mlp.gate_proj.biases": "model-00003-of-00005.safetensors",
281
+ "model.layers.19.feed_forward.switch_mlp.gate_proj.scales": "model-00003-of-00005.safetensors",
282
+ "model.layers.19.feed_forward.switch_mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
283
+ "model.layers.19.feed_forward.switch_mlp.up_proj.biases": "model-00003-of-00005.safetensors",
284
+ "model.layers.19.feed_forward.switch_mlp.up_proj.scales": "model-00003-of-00005.safetensors",
285
+ "model.layers.19.feed_forward.switch_mlp.up_proj.weight": "model-00003-of-00005.safetensors",
286
+ "model.layers.19.ffn_norm.weight": "model-00003-of-00005.safetensors",
287
+ "model.layers.19.operator_norm.weight": "model-00003-of-00005.safetensors",
288
+ "model.layers.2.feed_forward.expert_bias": "model-00001-of-00005.safetensors",
289
+ "model.layers.2.feed_forward.gate.biases": "model-00001-of-00005.safetensors",
290
+ "model.layers.2.feed_forward.gate.scales": "model-00001-of-00005.safetensors",
291
+ "model.layers.2.feed_forward.gate.weight": "model-00001-of-00005.safetensors",
292
+ "model.layers.2.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00005.safetensors",
293
+ "model.layers.2.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00005.safetensors",
294
+ "model.layers.2.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00005.safetensors",
295
+ "model.layers.2.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00005.safetensors",
296
+ "model.layers.2.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00005.safetensors",
297
+ "model.layers.2.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
298
+ "model.layers.2.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00005.safetensors",
299
+ "model.layers.2.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00005.safetensors",
300
+ "model.layers.2.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00005.safetensors",
301
+ "model.layers.2.ffn_norm.weight": "model-00001-of-00005.safetensors",
302
+ "model.layers.2.operator_norm.weight": "model-00001-of-00005.safetensors",
303
+ "model.layers.2.self_attn.k_layernorm.weight": "model-00001-of-00005.safetensors",
304
+ "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00005.safetensors",
305
+ "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00005.safetensors",
306
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
307
+ "model.layers.2.self_attn.out_proj.biases": "model-00001-of-00005.safetensors",
308
+ "model.layers.2.self_attn.out_proj.scales": "model-00001-of-00005.safetensors",
309
+ "model.layers.2.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
310
+ "model.layers.2.self_attn.q_layernorm.weight": "model-00001-of-00005.safetensors",
311
+ "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00005.safetensors",
312
+ "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00005.safetensors",
313
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
314
+ "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00005.safetensors",
315
+ "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00005.safetensors",
316
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
317
+ "model.layers.20.conv.conv.weight": "model-00003-of-00005.safetensors",
318
+ "model.layers.20.conv.in_proj.biases": "model-00003-of-00005.safetensors",
319
+ "model.layers.20.conv.in_proj.scales": "model-00003-of-00005.safetensors",
320
+ "model.layers.20.conv.in_proj.weight": "model-00003-of-00005.safetensors",
321
+ "model.layers.20.conv.out_proj.biases": "model-00003-of-00005.safetensors",
322
+ "model.layers.20.conv.out_proj.scales": "model-00003-of-00005.safetensors",
323
+ "model.layers.20.conv.out_proj.weight": "model-00003-of-00005.safetensors",
324
+ "model.layers.20.feed_forward.expert_bias": "model-00003-of-00005.safetensors",
325
+ "model.layers.20.feed_forward.gate.biases": "model-00003-of-00005.safetensors",
326
+ "model.layers.20.feed_forward.gate.scales": "model-00003-of-00005.safetensors",
327
+ "model.layers.20.feed_forward.gate.weight": "model-00003-of-00005.safetensors",
328
+ "model.layers.20.feed_forward.switch_mlp.down_proj.biases": "model-00003-of-00005.safetensors",
329
+ "model.layers.20.feed_forward.switch_mlp.down_proj.scales": "model-00003-of-00005.safetensors",
330
+ "model.layers.20.feed_forward.switch_mlp.down_proj.weight": "model-00003-of-00005.safetensors",
331
+ "model.layers.20.feed_forward.switch_mlp.gate_proj.biases": "model-00003-of-00005.safetensors",
332
+ "model.layers.20.feed_forward.switch_mlp.gate_proj.scales": "model-00003-of-00005.safetensors",
333
+ "model.layers.20.feed_forward.switch_mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
334
+ "model.layers.20.feed_forward.switch_mlp.up_proj.biases": "model-00003-of-00005.safetensors",
335
+ "model.layers.20.feed_forward.switch_mlp.up_proj.scales": "model-00003-of-00005.safetensors",
336
+ "model.layers.20.feed_forward.switch_mlp.up_proj.weight": "model-00003-of-00005.safetensors",
337
+ "model.layers.20.ffn_norm.weight": "model-00003-of-00005.safetensors",
338
+ "model.layers.20.operator_norm.weight": "model-00003-of-00005.safetensors",
339
+ "model.layers.21.conv.conv.weight": "model-00003-of-00005.safetensors",
340
+ "model.layers.21.conv.in_proj.biases": "model-00003-of-00005.safetensors",
341
+ "model.layers.21.conv.in_proj.scales": "model-00003-of-00005.safetensors",
342
+ "model.layers.21.conv.in_proj.weight": "model-00003-of-00005.safetensors",
343
+ "model.layers.21.conv.out_proj.biases": "model-00003-of-00005.safetensors",
344
+ "model.layers.21.conv.out_proj.scales": "model-00003-of-00005.safetensors",
345
+ "model.layers.21.conv.out_proj.weight": "model-00003-of-00005.safetensors",
346
+ "model.layers.21.feed_forward.expert_bias": "model-00003-of-00005.safetensors",
347
+ "model.layers.21.feed_forward.gate.biases": "model-00003-of-00005.safetensors",
348
+ "model.layers.21.feed_forward.gate.scales": "model-00003-of-00005.safetensors",
349
+ "model.layers.21.feed_forward.gate.weight": "model-00003-of-00005.safetensors",
350
+ "model.layers.21.feed_forward.switch_mlp.down_proj.biases": "model-00003-of-00005.safetensors",
351
+ "model.layers.21.feed_forward.switch_mlp.down_proj.scales": "model-00003-of-00005.safetensors",
352
+ "model.layers.21.feed_forward.switch_mlp.down_proj.weight": "model-00003-of-00005.safetensors",
353
+ "model.layers.21.feed_forward.switch_mlp.gate_proj.biases": "model-00003-of-00005.safetensors",
354
+ "model.layers.21.feed_forward.switch_mlp.gate_proj.scales": "model-00003-of-00005.safetensors",
355
+ "model.layers.21.feed_forward.switch_mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
356
+ "model.layers.21.feed_forward.switch_mlp.up_proj.biases": "model-00003-of-00005.safetensors",
357
+ "model.layers.21.feed_forward.switch_mlp.up_proj.scales": "model-00003-of-00005.safetensors",
358
+ "model.layers.21.feed_forward.switch_mlp.up_proj.weight": "model-00003-of-00005.safetensors",
359
+ "model.layers.21.ffn_norm.weight": "model-00003-of-00005.safetensors",
360
+ "model.layers.21.operator_norm.weight": "model-00003-of-00005.safetensors",
361
+ "model.layers.22.feed_forward.expert_bias": "model-00003-of-00005.safetensors",
362
+ "model.layers.22.feed_forward.gate.biases": "model-00003-of-00005.safetensors",
363
+ "model.layers.22.feed_forward.gate.scales": "model-00003-of-00005.safetensors",
364
+ "model.layers.22.feed_forward.gate.weight": "model-00003-of-00005.safetensors",
365
+ "model.layers.22.feed_forward.switch_mlp.down_proj.biases": "model-00003-of-00005.safetensors",
366
+ "model.layers.22.feed_forward.switch_mlp.down_proj.scales": "model-00003-of-00005.safetensors",
367
+ "model.layers.22.feed_forward.switch_mlp.down_proj.weight": "model-00003-of-00005.safetensors",
368
+ "model.layers.22.feed_forward.switch_mlp.gate_proj.biases": "model-00003-of-00005.safetensors",
369
+ "model.layers.22.feed_forward.switch_mlp.gate_proj.scales": "model-00003-of-00005.safetensors",
370
+ "model.layers.22.feed_forward.switch_mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
371
+ "model.layers.22.feed_forward.switch_mlp.up_proj.biases": "model-00003-of-00005.safetensors",
372
+ "model.layers.22.feed_forward.switch_mlp.up_proj.scales": "model-00003-of-00005.safetensors",
373
+ "model.layers.22.feed_forward.switch_mlp.up_proj.weight": "model-00003-of-00005.safetensors",
374
+ "model.layers.22.ffn_norm.weight": "model-00003-of-00005.safetensors",
375
+ "model.layers.22.operator_norm.weight": "model-00003-of-00005.safetensors",
376
+ "model.layers.22.self_attn.k_layernorm.weight": "model-00003-of-00005.safetensors",
377
+ "model.layers.22.self_attn.k_proj.biases": "model-00003-of-00005.safetensors",
378
+ "model.layers.22.self_attn.k_proj.scales": "model-00003-of-00005.safetensors",
379
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
380
+ "model.layers.22.self_attn.out_proj.biases": "model-00003-of-00005.safetensors",
381
+ "model.layers.22.self_attn.out_proj.scales": "model-00003-of-00005.safetensors",
382
+ "model.layers.22.self_attn.out_proj.weight": "model-00003-of-00005.safetensors",
383
+ "model.layers.22.self_attn.q_layernorm.weight": "model-00003-of-00005.safetensors",
384
+ "model.layers.22.self_attn.q_proj.biases": "model-00003-of-00005.safetensors",
385
+ "model.layers.22.self_attn.q_proj.scales": "model-00003-of-00005.safetensors",
386
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
387
+ "model.layers.22.self_attn.v_proj.biases": "model-00003-of-00005.safetensors",
388
+ "model.layers.22.self_attn.v_proj.scales": "model-00003-of-00005.safetensors",
389
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
390
+ "model.layers.23.conv.conv.weight": "model-00003-of-00005.safetensors",
391
+ "model.layers.23.conv.in_proj.biases": "model-00003-of-00005.safetensors",
392
+ "model.layers.23.conv.in_proj.scales": "model-00003-of-00005.safetensors",
393
+ "model.layers.23.conv.in_proj.weight": "model-00003-of-00005.safetensors",
394
+ "model.layers.23.conv.out_proj.biases": "model-00003-of-00005.safetensors",
395
+ "model.layers.23.conv.out_proj.scales": "model-00003-of-00005.safetensors",
396
+ "model.layers.23.conv.out_proj.weight": "model-00003-of-00005.safetensors",
397
+ "model.layers.23.feed_forward.expert_bias": "model-00003-of-00005.safetensors",
398
+ "model.layers.23.feed_forward.gate.biases": "model-00003-of-00005.safetensors",
399
+ "model.layers.23.feed_forward.gate.scales": "model-00003-of-00005.safetensors",
400
+ "model.layers.23.feed_forward.gate.weight": "model-00003-of-00005.safetensors",
401
+ "model.layers.23.feed_forward.switch_mlp.down_proj.biases": "model-00003-of-00005.safetensors",
402
+ "model.layers.23.feed_forward.switch_mlp.down_proj.scales": "model-00003-of-00005.safetensors",
403
+ "model.layers.23.feed_forward.switch_mlp.down_proj.weight": "model-00003-of-00005.safetensors",
404
+ "model.layers.23.feed_forward.switch_mlp.gate_proj.biases": "model-00003-of-00005.safetensors",
405
+ "model.layers.23.feed_forward.switch_mlp.gate_proj.scales": "model-00003-of-00005.safetensors",
406
+ "model.layers.23.feed_forward.switch_mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
407
+ "model.layers.23.feed_forward.switch_mlp.up_proj.biases": "model-00003-of-00005.safetensors",
408
+ "model.layers.23.feed_forward.switch_mlp.up_proj.scales": "model-00003-of-00005.safetensors",
409
+ "model.layers.23.feed_forward.switch_mlp.up_proj.weight": "model-00003-of-00005.safetensors",
410
+ "model.layers.23.ffn_norm.weight": "model-00003-of-00005.safetensors",
411
+ "model.layers.23.operator_norm.weight": "model-00003-of-00005.safetensors",
412
+ "model.layers.24.conv.conv.weight": "model-00003-of-00005.safetensors",
413
+ "model.layers.24.conv.in_proj.biases": "model-00003-of-00005.safetensors",
414
+ "model.layers.24.conv.in_proj.scales": "model-00003-of-00005.safetensors",
415
+ "model.layers.24.conv.in_proj.weight": "model-00003-of-00005.safetensors",
416
+ "model.layers.24.conv.out_proj.biases": "model-00003-of-00005.safetensors",
417
+ "model.layers.24.conv.out_proj.scales": "model-00003-of-00005.safetensors",
418
+ "model.layers.24.conv.out_proj.weight": "model-00003-of-00005.safetensors",
419
+ "model.layers.24.feed_forward.expert_bias": "model-00003-of-00005.safetensors",
420
+ "model.layers.24.feed_forward.gate.biases": "model-00003-of-00005.safetensors",
421
+ "model.layers.24.feed_forward.gate.scales": "model-00003-of-00005.safetensors",
422
+ "model.layers.24.feed_forward.gate.weight": "model-00003-of-00005.safetensors",
423
+ "model.layers.24.feed_forward.switch_mlp.down_proj.biases": "model-00003-of-00005.safetensors",
424
+ "model.layers.24.feed_forward.switch_mlp.down_proj.scales": "model-00003-of-00005.safetensors",
425
+ "model.layers.24.feed_forward.switch_mlp.down_proj.weight": "model-00003-of-00005.safetensors",
426
+ "model.layers.24.feed_forward.switch_mlp.gate_proj.biases": "model-00003-of-00005.safetensors",
427
+ "model.layers.24.feed_forward.switch_mlp.gate_proj.scales": "model-00003-of-00005.safetensors",
428
+ "model.layers.24.feed_forward.switch_mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
429
+ "model.layers.24.feed_forward.switch_mlp.up_proj.biases": "model-00003-of-00005.safetensors",
430
+ "model.layers.24.feed_forward.switch_mlp.up_proj.scales": "model-00003-of-00005.safetensors",
431
+ "model.layers.24.feed_forward.switch_mlp.up_proj.weight": "model-00003-of-00005.safetensors",
432
+ "model.layers.24.ffn_norm.weight": "model-00003-of-00005.safetensors",
433
+ "model.layers.24.operator_norm.weight": "model-00003-of-00005.safetensors",
434
+ "model.layers.25.conv.conv.weight": "model-00003-of-00005.safetensors",
435
+ "model.layers.25.conv.in_proj.biases": "model-00003-of-00005.safetensors",
436
+ "model.layers.25.conv.in_proj.scales": "model-00003-of-00005.safetensors",
437
+ "model.layers.25.conv.in_proj.weight": "model-00003-of-00005.safetensors",
438
+ "model.layers.25.conv.out_proj.biases": "model-00003-of-00005.safetensors",
439
+ "model.layers.25.conv.out_proj.scales": "model-00003-of-00005.safetensors",
440
+ "model.layers.25.conv.out_proj.weight": "model-00003-of-00005.safetensors",
441
+ "model.layers.25.feed_forward.expert_bias": "model-00004-of-00005.safetensors",
442
+ "model.layers.25.feed_forward.gate.biases": "model-00003-of-00005.safetensors",
443
+ "model.layers.25.feed_forward.gate.scales": "model-00003-of-00005.safetensors",
444
+ "model.layers.25.feed_forward.gate.weight": "model-00003-of-00005.safetensors",
445
+ "model.layers.25.feed_forward.switch_mlp.down_proj.biases": "model-00004-of-00005.safetensors",
446
+ "model.layers.25.feed_forward.switch_mlp.down_proj.scales": "model-00004-of-00005.safetensors",
447
+ "model.layers.25.feed_forward.switch_mlp.down_proj.weight": "model-00004-of-00005.safetensors",
448
+ "model.layers.25.feed_forward.switch_mlp.gate_proj.biases": "model-00003-of-00005.safetensors",
449
+ "model.layers.25.feed_forward.switch_mlp.gate_proj.scales": "model-00003-of-00005.safetensors",
450
+ "model.layers.25.feed_forward.switch_mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
451
+ "model.layers.25.feed_forward.switch_mlp.up_proj.biases": "model-00004-of-00005.safetensors",
452
+ "model.layers.25.feed_forward.switch_mlp.up_proj.scales": "model-00004-of-00005.safetensors",
453
+ "model.layers.25.feed_forward.switch_mlp.up_proj.weight": "model-00004-of-00005.safetensors",
454
+ "model.layers.25.ffn_norm.weight": "model-00004-of-00005.safetensors",
455
+ "model.layers.25.operator_norm.weight": "model-00004-of-00005.safetensors",
456
+ "model.layers.26.feed_forward.expert_bias": "model-00004-of-00005.safetensors",
457
+ "model.layers.26.feed_forward.gate.biases": "model-00004-of-00005.safetensors",
458
+ "model.layers.26.feed_forward.gate.scales": "model-00004-of-00005.safetensors",
459
+ "model.layers.26.feed_forward.gate.weight": "model-00004-of-00005.safetensors",
460
+ "model.layers.26.feed_forward.switch_mlp.down_proj.biases": "model-00004-of-00005.safetensors",
461
+ "model.layers.26.feed_forward.switch_mlp.down_proj.scales": "model-00004-of-00005.safetensors",
462
+ "model.layers.26.feed_forward.switch_mlp.down_proj.weight": "model-00004-of-00005.safetensors",
463
+ "model.layers.26.feed_forward.switch_mlp.gate_proj.biases": "model-00004-of-00005.safetensors",
464
+ "model.layers.26.feed_forward.switch_mlp.gate_proj.scales": "model-00004-of-00005.safetensors",
465
+ "model.layers.26.feed_forward.switch_mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
466
+ "model.layers.26.feed_forward.switch_mlp.up_proj.biases": "model-00004-of-00005.safetensors",
467
+ "model.layers.26.feed_forward.switch_mlp.up_proj.scales": "model-00004-of-00005.safetensors",
468
+ "model.layers.26.feed_forward.switch_mlp.up_proj.weight": "model-00004-of-00005.safetensors",
469
+ "model.layers.26.ffn_norm.weight": "model-00004-of-00005.safetensors",
470
+ "model.layers.26.operator_norm.weight": "model-00004-of-00005.safetensors",
471
+ "model.layers.26.self_attn.k_layernorm.weight": "model-00004-of-00005.safetensors",
472
+ "model.layers.26.self_attn.k_proj.biases": "model-00004-of-00005.safetensors",
473
+ "model.layers.26.self_attn.k_proj.scales": "model-00004-of-00005.safetensors",
474
+ "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
475
+ "model.layers.26.self_attn.out_proj.biases": "model-00004-of-00005.safetensors",
476
+ "model.layers.26.self_attn.out_proj.scales": "model-00004-of-00005.safetensors",
477
+ "model.layers.26.self_attn.out_proj.weight": "model-00004-of-00005.safetensors",
478
+ "model.layers.26.self_attn.q_layernorm.weight": "model-00004-of-00005.safetensors",
479
+ "model.layers.26.self_attn.q_proj.biases": "model-00004-of-00005.safetensors",
480
+ "model.layers.26.self_attn.q_proj.scales": "model-00004-of-00005.safetensors",
481
+ "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
482
+ "model.layers.26.self_attn.v_proj.biases": "model-00004-of-00005.safetensors",
483
+ "model.layers.26.self_attn.v_proj.scales": "model-00004-of-00005.safetensors",
484
+ "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
485
+ "model.layers.27.conv.conv.weight": "model-00004-of-00005.safetensors",
486
+ "model.layers.27.conv.in_proj.biases": "model-00004-of-00005.safetensors",
487
+ "model.layers.27.conv.in_proj.scales": "model-00004-of-00005.safetensors",
488
+ "model.layers.27.conv.in_proj.weight": "model-00004-of-00005.safetensors",
489
+ "model.layers.27.conv.out_proj.biases": "model-00004-of-00005.safetensors",
490
+ "model.layers.27.conv.out_proj.scales": "model-00004-of-00005.safetensors",
491
+ "model.layers.27.conv.out_proj.weight": "model-00004-of-00005.safetensors",
492
+ "model.layers.27.feed_forward.expert_bias": "model-00004-of-00005.safetensors",
493
+ "model.layers.27.feed_forward.gate.biases": "model-00004-of-00005.safetensors",
494
+ "model.layers.27.feed_forward.gate.scales": "model-00004-of-00005.safetensors",
495
+ "model.layers.27.feed_forward.gate.weight": "model-00004-of-00005.safetensors",
496
+ "model.layers.27.feed_forward.switch_mlp.down_proj.biases": "model-00004-of-00005.safetensors",
497
+ "model.layers.27.feed_forward.switch_mlp.down_proj.scales": "model-00004-of-00005.safetensors",
498
+ "model.layers.27.feed_forward.switch_mlp.down_proj.weight": "model-00004-of-00005.safetensors",
499
+ "model.layers.27.feed_forward.switch_mlp.gate_proj.biases": "model-00004-of-00005.safetensors",
500
+ "model.layers.27.feed_forward.switch_mlp.gate_proj.scales": "model-00004-of-00005.safetensors",
501
+ "model.layers.27.feed_forward.switch_mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
502
+ "model.layers.27.feed_forward.switch_mlp.up_proj.biases": "model-00004-of-00005.safetensors",
503
+ "model.layers.27.feed_forward.switch_mlp.up_proj.scales": "model-00004-of-00005.safetensors",
504
+ "model.layers.27.feed_forward.switch_mlp.up_proj.weight": "model-00004-of-00005.safetensors",
505
+ "model.layers.27.ffn_norm.weight": "model-00004-of-00005.safetensors",
506
+ "model.layers.27.operator_norm.weight": "model-00004-of-00005.safetensors",
507
+ "model.layers.28.conv.conv.weight": "model-00004-of-00005.safetensors",
508
+ "model.layers.28.conv.in_proj.biases": "model-00004-of-00005.safetensors",
509
+ "model.layers.28.conv.in_proj.scales": "model-00004-of-00005.safetensors",
510
+ "model.layers.28.conv.in_proj.weight": "model-00004-of-00005.safetensors",
511
+ "model.layers.28.conv.out_proj.biases": "model-00004-of-00005.safetensors",
512
+ "model.layers.28.conv.out_proj.scales": "model-00004-of-00005.safetensors",
513
+ "model.layers.28.conv.out_proj.weight": "model-00004-of-00005.safetensors",
514
+ "model.layers.28.feed_forward.expert_bias": "model-00004-of-00005.safetensors",
515
+ "model.layers.28.feed_forward.gate.biases": "model-00004-of-00005.safetensors",
516
+ "model.layers.28.feed_forward.gate.scales": "model-00004-of-00005.safetensors",
517
+ "model.layers.28.feed_forward.gate.weight": "model-00004-of-00005.safetensors",
518
+ "model.layers.28.feed_forward.switch_mlp.down_proj.biases": "model-00004-of-00005.safetensors",
519
+ "model.layers.28.feed_forward.switch_mlp.down_proj.scales": "model-00004-of-00005.safetensors",
520
+ "model.layers.28.feed_forward.switch_mlp.down_proj.weight": "model-00004-of-00005.safetensors",
521
+ "model.layers.28.feed_forward.switch_mlp.gate_proj.biases": "model-00004-of-00005.safetensors",
522
+ "model.layers.28.feed_forward.switch_mlp.gate_proj.scales": "model-00004-of-00005.safetensors",
523
+ "model.layers.28.feed_forward.switch_mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
524
+ "model.layers.28.feed_forward.switch_mlp.up_proj.biases": "model-00004-of-00005.safetensors",
525
+ "model.layers.28.feed_forward.switch_mlp.up_proj.scales": "model-00004-of-00005.safetensors",
526
+ "model.layers.28.feed_forward.switch_mlp.up_proj.weight": "model-00004-of-00005.safetensors",
527
+ "model.layers.28.ffn_norm.weight": "model-00004-of-00005.safetensors",
528
+ "model.layers.28.operator_norm.weight": "model-00004-of-00005.safetensors",
529
+ "model.layers.29.conv.conv.weight": "model-00004-of-00005.safetensors",
530
+ "model.layers.29.conv.in_proj.biases": "model-00004-of-00005.safetensors",
531
+ "model.layers.29.conv.in_proj.scales": "model-00004-of-00005.safetensors",
532
+ "model.layers.29.conv.in_proj.weight": "model-00004-of-00005.safetensors",
533
+ "model.layers.29.conv.out_proj.biases": "model-00004-of-00005.safetensors",
534
+ "model.layers.29.conv.out_proj.scales": "model-00004-of-00005.safetensors",
535
+ "model.layers.29.conv.out_proj.weight": "model-00004-of-00005.safetensors",
536
+ "model.layers.29.feed_forward.expert_bias": "model-00004-of-00005.safetensors",
537
+ "model.layers.29.feed_forward.gate.biases": "model-00004-of-00005.safetensors",
538
+ "model.layers.29.feed_forward.gate.scales": "model-00004-of-00005.safetensors",
539
+ "model.layers.29.feed_forward.gate.weight": "model-00004-of-00005.safetensors",
540
+ "model.layers.29.feed_forward.switch_mlp.down_proj.biases": "model-00004-of-00005.safetensors",
541
+ "model.layers.29.feed_forward.switch_mlp.down_proj.scales": "model-00004-of-00005.safetensors",
542
+ "model.layers.29.feed_forward.switch_mlp.down_proj.weight": "model-00004-of-00005.safetensors",
543
+ "model.layers.29.feed_forward.switch_mlp.gate_proj.biases": "model-00004-of-00005.safetensors",
544
+ "model.layers.29.feed_forward.switch_mlp.gate_proj.scales": "model-00004-of-00005.safetensors",
545
+ "model.layers.29.feed_forward.switch_mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
546
+ "model.layers.29.feed_forward.switch_mlp.up_proj.biases": "model-00004-of-00005.safetensors",
547
+ "model.layers.29.feed_forward.switch_mlp.up_proj.scales": "model-00004-of-00005.safetensors",
548
+ "model.layers.29.feed_forward.switch_mlp.up_proj.weight": "model-00004-of-00005.safetensors",
549
+ "model.layers.29.ffn_norm.weight": "model-00004-of-00005.safetensors",
550
+ "model.layers.29.operator_norm.weight": "model-00004-of-00005.safetensors",
551
+ "model.layers.3.conv.conv.weight": "model-00001-of-00005.safetensors",
552
+ "model.layers.3.conv.in_proj.biases": "model-00001-of-00005.safetensors",
553
+ "model.layers.3.conv.in_proj.scales": "model-00001-of-00005.safetensors",
554
+ "model.layers.3.conv.in_proj.weight": "model-00001-of-00005.safetensors",
555
+ "model.layers.3.conv.out_proj.biases": "model-00001-of-00005.safetensors",
556
+ "model.layers.3.conv.out_proj.scales": "model-00001-of-00005.safetensors",
557
+ "model.layers.3.conv.out_proj.weight": "model-00001-of-00005.safetensors",
558
+ "model.layers.3.feed_forward.expert_bias": "model-00001-of-00005.safetensors",
559
+ "model.layers.3.feed_forward.gate.biases": "model-00001-of-00005.safetensors",
560
+ "model.layers.3.feed_forward.gate.scales": "model-00001-of-00005.safetensors",
561
+ "model.layers.3.feed_forward.gate.weight": "model-00001-of-00005.safetensors",
562
+ "model.layers.3.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00005.safetensors",
563
+ "model.layers.3.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00005.safetensors",
564
+ "model.layers.3.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00005.safetensors",
565
+ "model.layers.3.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00005.safetensors",
566
+ "model.layers.3.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00005.safetensors",
567
+ "model.layers.3.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
568
+ "model.layers.3.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00005.safetensors",
569
+ "model.layers.3.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00005.safetensors",
570
+ "model.layers.3.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00005.safetensors",
571
+ "model.layers.3.ffn_norm.weight": "model-00001-of-00005.safetensors",
572
+ "model.layers.3.operator_norm.weight": "model-00001-of-00005.safetensors",
573
+ "model.layers.30.feed_forward.expert_bias": "model-00004-of-00005.safetensors",
574
+ "model.layers.30.feed_forward.gate.biases": "model-00004-of-00005.safetensors",
575
+ "model.layers.30.feed_forward.gate.scales": "model-00004-of-00005.safetensors",
576
+ "model.layers.30.feed_forward.gate.weight": "model-00004-of-00005.safetensors",
577
+ "model.layers.30.feed_forward.switch_mlp.down_proj.biases": "model-00004-of-00005.safetensors",
578
+ "model.layers.30.feed_forward.switch_mlp.down_proj.scales": "model-00004-of-00005.safetensors",
579
+ "model.layers.30.feed_forward.switch_mlp.down_proj.weight": "model-00004-of-00005.safetensors",
580
+ "model.layers.30.feed_forward.switch_mlp.gate_proj.biases": "model-00004-of-00005.safetensors",
581
+ "model.layers.30.feed_forward.switch_mlp.gate_proj.scales": "model-00004-of-00005.safetensors",
582
+ "model.layers.30.feed_forward.switch_mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
583
+ "model.layers.30.feed_forward.switch_mlp.up_proj.biases": "model-00004-of-00005.safetensors",
584
+ "model.layers.30.feed_forward.switch_mlp.up_proj.scales": "model-00004-of-00005.safetensors",
585
+ "model.layers.30.feed_forward.switch_mlp.up_proj.weight": "model-00004-of-00005.safetensors",
586
+ "model.layers.30.ffn_norm.weight": "model-00004-of-00005.safetensors",
587
+ "model.layers.30.operator_norm.weight": "model-00004-of-00005.safetensors",
588
+ "model.layers.30.self_attn.k_layernorm.weight": "model-00004-of-00005.safetensors",
589
+ "model.layers.30.self_attn.k_proj.biases": "model-00004-of-00005.safetensors",
590
+ "model.layers.30.self_attn.k_proj.scales": "model-00004-of-00005.safetensors",
591
+ "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
592
+ "model.layers.30.self_attn.out_proj.biases": "model-00004-of-00005.safetensors",
593
+ "model.layers.30.self_attn.out_proj.scales": "model-00004-of-00005.safetensors",
594
+ "model.layers.30.self_attn.out_proj.weight": "model-00004-of-00005.safetensors",
595
+ "model.layers.30.self_attn.q_layernorm.weight": "model-00004-of-00005.safetensors",
596
+ "model.layers.30.self_attn.q_proj.biases": "model-00004-of-00005.safetensors",
597
+ "model.layers.30.self_attn.q_proj.scales": "model-00004-of-00005.safetensors",
598
+ "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
599
+ "model.layers.30.self_attn.v_proj.biases": "model-00004-of-00005.safetensors",
600
+ "model.layers.30.self_attn.v_proj.scales": "model-00004-of-00005.safetensors",
601
+ "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
602
+ "model.layers.31.conv.conv.weight": "model-00004-of-00005.safetensors",
603
+ "model.layers.31.conv.in_proj.biases": "model-00004-of-00005.safetensors",
604
+ "model.layers.31.conv.in_proj.scales": "model-00004-of-00005.safetensors",
605
+ "model.layers.31.conv.in_proj.weight": "model-00004-of-00005.safetensors",
606
+ "model.layers.31.conv.out_proj.biases": "model-00004-of-00005.safetensors",
607
+ "model.layers.31.conv.out_proj.scales": "model-00004-of-00005.safetensors",
608
+ "model.layers.31.conv.out_proj.weight": "model-00004-of-00005.safetensors",
609
+ "model.layers.31.feed_forward.expert_bias": "model-00004-of-00005.safetensors",
610
+ "model.layers.31.feed_forward.gate.biases": "model-00004-of-00005.safetensors",
611
+ "model.layers.31.feed_forward.gate.scales": "model-00004-of-00005.safetensors",
612
+ "model.layers.31.feed_forward.gate.weight": "model-00004-of-00005.safetensors",
613
+ "model.layers.31.feed_forward.switch_mlp.down_proj.biases": "model-00004-of-00005.safetensors",
614
+ "model.layers.31.feed_forward.switch_mlp.down_proj.scales": "model-00004-of-00005.safetensors",
615
+ "model.layers.31.feed_forward.switch_mlp.down_proj.weight": "model-00004-of-00005.safetensors",
616
+ "model.layers.31.feed_forward.switch_mlp.gate_proj.biases": "model-00004-of-00005.safetensors",
617
+ "model.layers.31.feed_forward.switch_mlp.gate_proj.scales": "model-00004-of-00005.safetensors",
618
+ "model.layers.31.feed_forward.switch_mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
619
+ "model.layers.31.feed_forward.switch_mlp.up_proj.biases": "model-00004-of-00005.safetensors",
620
+ "model.layers.31.feed_forward.switch_mlp.up_proj.scales": "model-00004-of-00005.safetensors",
621
+ "model.layers.31.feed_forward.switch_mlp.up_proj.weight": "model-00004-of-00005.safetensors",
622
+ "model.layers.31.ffn_norm.weight": "model-00004-of-00005.safetensors",
623
+ "model.layers.31.operator_norm.weight": "model-00004-of-00005.safetensors",
624
+ "model.layers.32.conv.conv.weight": "model-00004-of-00005.safetensors",
625
+ "model.layers.32.conv.in_proj.biases": "model-00004-of-00005.safetensors",
626
+ "model.layers.32.conv.in_proj.scales": "model-00004-of-00005.safetensors",
627
+ "model.layers.32.conv.in_proj.weight": "model-00004-of-00005.safetensors",
628
+ "model.layers.32.conv.out_proj.biases": "model-00004-of-00005.safetensors",
629
+ "model.layers.32.conv.out_proj.scales": "model-00004-of-00005.safetensors",
630
+ "model.layers.32.conv.out_proj.weight": "model-00004-of-00005.safetensors",
631
+ "model.layers.32.feed_forward.expert_bias": "model-00004-of-00005.safetensors",
632
+ "model.layers.32.feed_forward.gate.biases": "model-00004-of-00005.safetensors",
633
+ "model.layers.32.feed_forward.gate.scales": "model-00004-of-00005.safetensors",
634
+ "model.layers.32.feed_forward.gate.weight": "model-00004-of-00005.safetensors",
635
+ "model.layers.32.feed_forward.switch_mlp.down_proj.biases": "model-00004-of-00005.safetensors",
636
+ "model.layers.32.feed_forward.switch_mlp.down_proj.scales": "model-00004-of-00005.safetensors",
637
+ "model.layers.32.feed_forward.switch_mlp.down_proj.weight": "model-00004-of-00005.safetensors",
638
+ "model.layers.32.feed_forward.switch_mlp.gate_proj.biases": "model-00004-of-00005.safetensors",
639
+ "model.layers.32.feed_forward.switch_mlp.gate_proj.scales": "model-00004-of-00005.safetensors",
640
+ "model.layers.32.feed_forward.switch_mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
641
+ "model.layers.32.feed_forward.switch_mlp.up_proj.biases": "model-00004-of-00005.safetensors",
642
+ "model.layers.32.feed_forward.switch_mlp.up_proj.scales": "model-00004-of-00005.safetensors",
643
+ "model.layers.32.feed_forward.switch_mlp.up_proj.weight": "model-00004-of-00005.safetensors",
644
+ "model.layers.32.ffn_norm.weight": "model-00004-of-00005.safetensors",
645
+ "model.layers.32.operator_norm.weight": "model-00004-of-00005.safetensors",
646
+ "model.layers.33.conv.conv.weight": "model-00004-of-00005.safetensors",
647
+ "model.layers.33.conv.in_proj.biases": "model-00004-of-00005.safetensors",
648
+ "model.layers.33.conv.in_proj.scales": "model-00004-of-00005.safetensors",
649
+ "model.layers.33.conv.in_proj.weight": "model-00004-of-00005.safetensors",
650
+ "model.layers.33.conv.out_proj.biases": "model-00004-of-00005.safetensors",
651
+ "model.layers.33.conv.out_proj.scales": "model-00004-of-00005.safetensors",
652
+ "model.layers.33.conv.out_proj.weight": "model-00004-of-00005.safetensors",
653
+ "model.layers.33.feed_forward.expert_bias": "model-00005-of-00005.safetensors",
654
+ "model.layers.33.feed_forward.gate.biases": "model-00004-of-00005.safetensors",
655
+ "model.layers.33.feed_forward.gate.scales": "model-00004-of-00005.safetensors",
656
+ "model.layers.33.feed_forward.gate.weight": "model-00004-of-00005.safetensors",
657
+ "model.layers.33.feed_forward.switch_mlp.down_proj.biases": "model-00005-of-00005.safetensors",
658
+ "model.layers.33.feed_forward.switch_mlp.down_proj.scales": "model-00005-of-00005.safetensors",
659
+ "model.layers.33.feed_forward.switch_mlp.down_proj.weight": "model-00005-of-00005.safetensors",
660
+ "model.layers.33.feed_forward.switch_mlp.gate_proj.biases": "model-00004-of-00005.safetensors",
661
+ "model.layers.33.feed_forward.switch_mlp.gate_proj.scales": "model-00004-of-00005.safetensors",
662
+ "model.layers.33.feed_forward.switch_mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
663
+ "model.layers.33.feed_forward.switch_mlp.up_proj.biases": "model-00005-of-00005.safetensors",
664
+ "model.layers.33.feed_forward.switch_mlp.up_proj.scales": "model-00005-of-00005.safetensors",
665
+ "model.layers.33.feed_forward.switch_mlp.up_proj.weight": "model-00005-of-00005.safetensors",
666
+ "model.layers.33.ffn_norm.weight": "model-00005-of-00005.safetensors",
667
+ "model.layers.33.operator_norm.weight": "model-00005-of-00005.safetensors",
668
+ "model.layers.34.feed_forward.expert_bias": "model-00005-of-00005.safetensors",
669
+ "model.layers.34.feed_forward.gate.biases": "model-00005-of-00005.safetensors",
670
+ "model.layers.34.feed_forward.gate.scales": "model-00005-of-00005.safetensors",
671
+ "model.layers.34.feed_forward.gate.weight": "model-00005-of-00005.safetensors",
672
+ "model.layers.34.feed_forward.switch_mlp.down_proj.biases": "model-00005-of-00005.safetensors",
673
+ "model.layers.34.feed_forward.switch_mlp.down_proj.scales": "model-00005-of-00005.safetensors",
674
+ "model.layers.34.feed_forward.switch_mlp.down_proj.weight": "model-00005-of-00005.safetensors",
675
+ "model.layers.34.feed_forward.switch_mlp.gate_proj.biases": "model-00005-of-00005.safetensors",
676
+ "model.layers.34.feed_forward.switch_mlp.gate_proj.scales": "model-00005-of-00005.safetensors",
677
+ "model.layers.34.feed_forward.switch_mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
678
+ "model.layers.34.feed_forward.switch_mlp.up_proj.biases": "model-00005-of-00005.safetensors",
679
+ "model.layers.34.feed_forward.switch_mlp.up_proj.scales": "model-00005-of-00005.safetensors",
680
+ "model.layers.34.feed_forward.switch_mlp.up_proj.weight": "model-00005-of-00005.safetensors",
681
+ "model.layers.34.ffn_norm.weight": "model-00005-of-00005.safetensors",
682
+ "model.layers.34.operator_norm.weight": "model-00005-of-00005.safetensors",
683
+ "model.layers.34.self_attn.k_layernorm.weight": "model-00005-of-00005.safetensors",
684
+ "model.layers.34.self_attn.k_proj.biases": "model-00005-of-00005.safetensors",
685
+ "model.layers.34.self_attn.k_proj.scales": "model-00005-of-00005.safetensors",
686
+ "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
687
+ "model.layers.34.self_attn.out_proj.biases": "model-00005-of-00005.safetensors",
688
+ "model.layers.34.self_attn.out_proj.scales": "model-00005-of-00005.safetensors",
689
+ "model.layers.34.self_attn.out_proj.weight": "model-00005-of-00005.safetensors",
690
+ "model.layers.34.self_attn.q_layernorm.weight": "model-00005-of-00005.safetensors",
691
+ "model.layers.34.self_attn.q_proj.biases": "model-00005-of-00005.safetensors",
692
+ "model.layers.34.self_attn.q_proj.scales": "model-00005-of-00005.safetensors",
693
+ "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
694
+ "model.layers.34.self_attn.v_proj.biases": "model-00005-of-00005.safetensors",
695
+ "model.layers.34.self_attn.v_proj.scales": "model-00005-of-00005.safetensors",
696
+ "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
697
+ "model.layers.35.conv.conv.weight": "model-00005-of-00005.safetensors",
698
+ "model.layers.35.conv.in_proj.biases": "model-00005-of-00005.safetensors",
699
+ "model.layers.35.conv.in_proj.scales": "model-00005-of-00005.safetensors",
700
+ "model.layers.35.conv.in_proj.weight": "model-00005-of-00005.safetensors",
701
+ "model.layers.35.conv.out_proj.biases": "model-00005-of-00005.safetensors",
702
+ "model.layers.35.conv.out_proj.scales": "model-00005-of-00005.safetensors",
703
+ "model.layers.35.conv.out_proj.weight": "model-00005-of-00005.safetensors",
704
+ "model.layers.35.feed_forward.expert_bias": "model-00005-of-00005.safetensors",
705
+ "model.layers.35.feed_forward.gate.biases": "model-00005-of-00005.safetensors",
706
+ "model.layers.35.feed_forward.gate.scales": "model-00005-of-00005.safetensors",
707
+ "model.layers.35.feed_forward.gate.weight": "model-00005-of-00005.safetensors",
708
+ "model.layers.35.feed_forward.switch_mlp.down_proj.biases": "model-00005-of-00005.safetensors",
709
+ "model.layers.35.feed_forward.switch_mlp.down_proj.scales": "model-00005-of-00005.safetensors",
710
+ "model.layers.35.feed_forward.switch_mlp.down_proj.weight": "model-00005-of-00005.safetensors",
711
+ "model.layers.35.feed_forward.switch_mlp.gate_proj.biases": "model-00005-of-00005.safetensors",
712
+ "model.layers.35.feed_forward.switch_mlp.gate_proj.scales": "model-00005-of-00005.safetensors",
713
+ "model.layers.35.feed_forward.switch_mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
714
+ "model.layers.35.feed_forward.switch_mlp.up_proj.biases": "model-00005-of-00005.safetensors",
715
+ "model.layers.35.feed_forward.switch_mlp.up_proj.scales": "model-00005-of-00005.safetensors",
716
+ "model.layers.35.feed_forward.switch_mlp.up_proj.weight": "model-00005-of-00005.safetensors",
717
+ "model.layers.35.ffn_norm.weight": "model-00005-of-00005.safetensors",
718
+ "model.layers.35.operator_norm.weight": "model-00005-of-00005.safetensors",
719
+ "model.layers.36.conv.conv.weight": "model-00005-of-00005.safetensors",
720
+ "model.layers.36.conv.in_proj.biases": "model-00005-of-00005.safetensors",
721
+ "model.layers.36.conv.in_proj.scales": "model-00005-of-00005.safetensors",
722
+ "model.layers.36.conv.in_proj.weight": "model-00005-of-00005.safetensors",
723
+ "model.layers.36.conv.out_proj.biases": "model-00005-of-00005.safetensors",
724
+ "model.layers.36.conv.out_proj.scales": "model-00005-of-00005.safetensors",
725
+ "model.layers.36.conv.out_proj.weight": "model-00005-of-00005.safetensors",
726
+ "model.layers.36.feed_forward.expert_bias": "model-00005-of-00005.safetensors",
727
+ "model.layers.36.feed_forward.gate.biases": "model-00005-of-00005.safetensors",
728
+ "model.layers.36.feed_forward.gate.scales": "model-00005-of-00005.safetensors",
729
+ "model.layers.36.feed_forward.gate.weight": "model-00005-of-00005.safetensors",
730
+ "model.layers.36.feed_forward.switch_mlp.down_proj.biases": "model-00005-of-00005.safetensors",
731
+ "model.layers.36.feed_forward.switch_mlp.down_proj.scales": "model-00005-of-00005.safetensors",
732
+ "model.layers.36.feed_forward.switch_mlp.down_proj.weight": "model-00005-of-00005.safetensors",
733
+ "model.layers.36.feed_forward.switch_mlp.gate_proj.biases": "model-00005-of-00005.safetensors",
734
+ "model.layers.36.feed_forward.switch_mlp.gate_proj.scales": "model-00005-of-00005.safetensors",
735
+ "model.layers.36.feed_forward.switch_mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
736
+ "model.layers.36.feed_forward.switch_mlp.up_proj.biases": "model-00005-of-00005.safetensors",
737
+ "model.layers.36.feed_forward.switch_mlp.up_proj.scales": "model-00005-of-00005.safetensors",
738
+ "model.layers.36.feed_forward.switch_mlp.up_proj.weight": "model-00005-of-00005.safetensors",
739
+ "model.layers.36.ffn_norm.weight": "model-00005-of-00005.safetensors",
740
+ "model.layers.36.operator_norm.weight": "model-00005-of-00005.safetensors",
741
+ "model.layers.37.conv.conv.weight": "model-00005-of-00005.safetensors",
742
+ "model.layers.37.conv.in_proj.biases": "model-00005-of-00005.safetensors",
743
+ "model.layers.37.conv.in_proj.scales": "model-00005-of-00005.safetensors",
744
+ "model.layers.37.conv.in_proj.weight": "model-00005-of-00005.safetensors",
745
+ "model.layers.37.conv.out_proj.biases": "model-00005-of-00005.safetensors",
746
+ "model.layers.37.conv.out_proj.scales": "model-00005-of-00005.safetensors",
747
+ "model.layers.37.conv.out_proj.weight": "model-00005-of-00005.safetensors",
748
+ "model.layers.37.feed_forward.expert_bias": "model-00005-of-00005.safetensors",
749
+ "model.layers.37.feed_forward.gate.biases": "model-00005-of-00005.safetensors",
750
+ "model.layers.37.feed_forward.gate.scales": "model-00005-of-00005.safetensors",
751
+ "model.layers.37.feed_forward.gate.weight": "model-00005-of-00005.safetensors",
752
+ "model.layers.37.feed_forward.switch_mlp.down_proj.biases": "model-00005-of-00005.safetensors",
753
+ "model.layers.37.feed_forward.switch_mlp.down_proj.scales": "model-00005-of-00005.safetensors",
754
+ "model.layers.37.feed_forward.switch_mlp.down_proj.weight": "model-00005-of-00005.safetensors",
755
+ "model.layers.37.feed_forward.switch_mlp.gate_proj.biases": "model-00005-of-00005.safetensors",
756
+ "model.layers.37.feed_forward.switch_mlp.gate_proj.scales": "model-00005-of-00005.safetensors",
757
+ "model.layers.37.feed_forward.switch_mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
758
+ "model.layers.37.feed_forward.switch_mlp.up_proj.biases": "model-00005-of-00005.safetensors",
759
+ "model.layers.37.feed_forward.switch_mlp.up_proj.scales": "model-00005-of-00005.safetensors",
760
+ "model.layers.37.feed_forward.switch_mlp.up_proj.weight": "model-00005-of-00005.safetensors",
761
+ "model.layers.37.ffn_norm.weight": "model-00005-of-00005.safetensors",
762
+ "model.layers.37.operator_norm.weight": "model-00005-of-00005.safetensors",
763
+ "model.layers.38.feed_forward.expert_bias": "model-00005-of-00005.safetensors",
764
+ "model.layers.38.feed_forward.gate.biases": "model-00005-of-00005.safetensors",
765
+ "model.layers.38.feed_forward.gate.scales": "model-00005-of-00005.safetensors",
766
+ "model.layers.38.feed_forward.gate.weight": "model-00005-of-00005.safetensors",
767
+ "model.layers.38.feed_forward.switch_mlp.down_proj.biases": "model-00005-of-00005.safetensors",
768
+ "model.layers.38.feed_forward.switch_mlp.down_proj.scales": "model-00005-of-00005.safetensors",
769
+ "model.layers.38.feed_forward.switch_mlp.down_proj.weight": "model-00005-of-00005.safetensors",
770
+ "model.layers.38.feed_forward.switch_mlp.gate_proj.biases": "model-00005-of-00005.safetensors",
771
+ "model.layers.38.feed_forward.switch_mlp.gate_proj.scales": "model-00005-of-00005.safetensors",
772
+ "model.layers.38.feed_forward.switch_mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
773
+ "model.layers.38.feed_forward.switch_mlp.up_proj.biases": "model-00005-of-00005.safetensors",
774
+ "model.layers.38.feed_forward.switch_mlp.up_proj.scales": "model-00005-of-00005.safetensors",
775
+ "model.layers.38.feed_forward.switch_mlp.up_proj.weight": "model-00005-of-00005.safetensors",
776
+ "model.layers.38.ffn_norm.weight": "model-00005-of-00005.safetensors",
777
+ "model.layers.38.operator_norm.weight": "model-00005-of-00005.safetensors",
778
+ "model.layers.38.self_attn.k_layernorm.weight": "model-00005-of-00005.safetensors",
779
+ "model.layers.38.self_attn.k_proj.biases": "model-00005-of-00005.safetensors",
780
+ "model.layers.38.self_attn.k_proj.scales": "model-00005-of-00005.safetensors",
781
+ "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
782
+ "model.layers.38.self_attn.out_proj.biases": "model-00005-of-00005.safetensors",
783
+ "model.layers.38.self_attn.out_proj.scales": "model-00005-of-00005.safetensors",
784
+ "model.layers.38.self_attn.out_proj.weight": "model-00005-of-00005.safetensors",
785
+ "model.layers.38.self_attn.q_layernorm.weight": "model-00005-of-00005.safetensors",
786
+ "model.layers.38.self_attn.q_proj.biases": "model-00005-of-00005.safetensors",
787
+ "model.layers.38.self_attn.q_proj.scales": "model-00005-of-00005.safetensors",
788
+ "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
789
+ "model.layers.38.self_attn.v_proj.biases": "model-00005-of-00005.safetensors",
790
+ "model.layers.38.self_attn.v_proj.scales": "model-00005-of-00005.safetensors",
791
+ "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
792
+ "model.layers.39.conv.conv.weight": "model-00005-of-00005.safetensors",
793
+ "model.layers.39.conv.in_proj.biases": "model-00005-of-00005.safetensors",
794
+ "model.layers.39.conv.in_proj.scales": "model-00005-of-00005.safetensors",
795
+ "model.layers.39.conv.in_proj.weight": "model-00005-of-00005.safetensors",
796
+ "model.layers.39.conv.out_proj.biases": "model-00005-of-00005.safetensors",
797
+ "model.layers.39.conv.out_proj.scales": "model-00005-of-00005.safetensors",
798
+ "model.layers.39.conv.out_proj.weight": "model-00005-of-00005.safetensors",
799
+ "model.layers.39.feed_forward.expert_bias": "model-00005-of-00005.safetensors",
800
+ "model.layers.39.feed_forward.gate.biases": "model-00005-of-00005.safetensors",
801
+ "model.layers.39.feed_forward.gate.scales": "model-00005-of-00005.safetensors",
802
+ "model.layers.39.feed_forward.gate.weight": "model-00005-of-00005.safetensors",
803
+ "model.layers.39.feed_forward.switch_mlp.down_proj.biases": "model-00005-of-00005.safetensors",
804
+ "model.layers.39.feed_forward.switch_mlp.down_proj.scales": "model-00005-of-00005.safetensors",
805
+ "model.layers.39.feed_forward.switch_mlp.down_proj.weight": "model-00005-of-00005.safetensors",
806
+ "model.layers.39.feed_forward.switch_mlp.gate_proj.biases": "model-00005-of-00005.safetensors",
807
+ "model.layers.39.feed_forward.switch_mlp.gate_proj.scales": "model-00005-of-00005.safetensors",
808
+ "model.layers.39.feed_forward.switch_mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
809
+ "model.layers.39.feed_forward.switch_mlp.up_proj.biases": "model-00005-of-00005.safetensors",
810
+ "model.layers.39.feed_forward.switch_mlp.up_proj.scales": "model-00005-of-00005.safetensors",
811
+ "model.layers.39.feed_forward.switch_mlp.up_proj.weight": "model-00005-of-00005.safetensors",
812
+ "model.layers.39.ffn_norm.weight": "model-00005-of-00005.safetensors",
813
+ "model.layers.39.operator_norm.weight": "model-00005-of-00005.safetensors",
814
+ "model.layers.4.conv.conv.weight": "model-00001-of-00005.safetensors",
815
+ "model.layers.4.conv.in_proj.biases": "model-00001-of-00005.safetensors",
816
+ "model.layers.4.conv.in_proj.scales": "model-00001-of-00005.safetensors",
817
+ "model.layers.4.conv.in_proj.weight": "model-00001-of-00005.safetensors",
818
+ "model.layers.4.conv.out_proj.biases": "model-00001-of-00005.safetensors",
819
+ "model.layers.4.conv.out_proj.scales": "model-00001-of-00005.safetensors",
820
+ "model.layers.4.conv.out_proj.weight": "model-00001-of-00005.safetensors",
821
+ "model.layers.4.feed_forward.expert_bias": "model-00001-of-00005.safetensors",
822
+ "model.layers.4.feed_forward.gate.biases": "model-00001-of-00005.safetensors",
823
+ "model.layers.4.feed_forward.gate.scales": "model-00001-of-00005.safetensors",
824
+ "model.layers.4.feed_forward.gate.weight": "model-00001-of-00005.safetensors",
825
+ "model.layers.4.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00005.safetensors",
826
+ "model.layers.4.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00005.safetensors",
827
+ "model.layers.4.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00005.safetensors",
828
+ "model.layers.4.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00005.safetensors",
829
+ "model.layers.4.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00005.safetensors",
830
+ "model.layers.4.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
831
+ "model.layers.4.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00005.safetensors",
832
+ "model.layers.4.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00005.safetensors",
833
+ "model.layers.4.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00005.safetensors",
834
+ "model.layers.4.ffn_norm.weight": "model-00001-of-00005.safetensors",
835
+ "model.layers.4.operator_norm.weight": "model-00001-of-00005.safetensors",
836
+ "model.layers.5.conv.conv.weight": "model-00001-of-00005.safetensors",
837
+ "model.layers.5.conv.in_proj.biases": "model-00001-of-00005.safetensors",
838
+ "model.layers.5.conv.in_proj.scales": "model-00001-of-00005.safetensors",
839
+ "model.layers.5.conv.in_proj.weight": "model-00001-of-00005.safetensors",
840
+ "model.layers.5.conv.out_proj.biases": "model-00001-of-00005.safetensors",
841
+ "model.layers.5.conv.out_proj.scales": "model-00001-of-00005.safetensors",
842
+ "model.layers.5.conv.out_proj.weight": "model-00001-of-00005.safetensors",
843
+ "model.layers.5.feed_forward.expert_bias": "model-00001-of-00005.safetensors",
844
+ "model.layers.5.feed_forward.gate.biases": "model-00001-of-00005.safetensors",
845
+ "model.layers.5.feed_forward.gate.scales": "model-00001-of-00005.safetensors",
846
+ "model.layers.5.feed_forward.gate.weight": "model-00001-of-00005.safetensors",
847
+ "model.layers.5.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00005.safetensors",
848
+ "model.layers.5.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00005.safetensors",
849
+ "model.layers.5.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00005.safetensors",
850
+ "model.layers.5.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00005.safetensors",
851
+ "model.layers.5.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00005.safetensors",
852
+ "model.layers.5.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
853
+ "model.layers.5.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00005.safetensors",
854
+ "model.layers.5.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00005.safetensors",
855
+ "model.layers.5.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00005.safetensors",
856
+ "model.layers.5.ffn_norm.weight": "model-00001-of-00005.safetensors",
857
+ "model.layers.5.operator_norm.weight": "model-00001-of-00005.safetensors",
858
+ "model.layers.6.feed_forward.expert_bias": "model-00001-of-00005.safetensors",
859
+ "model.layers.6.feed_forward.gate.biases": "model-00001-of-00005.safetensors",
860
+ "model.layers.6.feed_forward.gate.scales": "model-00001-of-00005.safetensors",
861
+ "model.layers.6.feed_forward.gate.weight": "model-00001-of-00005.safetensors",
862
+ "model.layers.6.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00005.safetensors",
863
+ "model.layers.6.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00005.safetensors",
864
+ "model.layers.6.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00005.safetensors",
865
+ "model.layers.6.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00005.safetensors",
866
+ "model.layers.6.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00005.safetensors",
867
+ "model.layers.6.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
868
+ "model.layers.6.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00005.safetensors",
869
+ "model.layers.6.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00005.safetensors",
870
+ "model.layers.6.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00005.safetensors",
871
+ "model.layers.6.ffn_norm.weight": "model-00001-of-00005.safetensors",
872
+ "model.layers.6.operator_norm.weight": "model-00001-of-00005.safetensors",
873
+ "model.layers.6.self_attn.k_layernorm.weight": "model-00001-of-00005.safetensors",
874
+ "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00005.safetensors",
875
+ "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00005.safetensors",
876
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
877
+ "model.layers.6.self_attn.out_proj.biases": "model-00001-of-00005.safetensors",
878
+ "model.layers.6.self_attn.out_proj.scales": "model-00001-of-00005.safetensors",
879
+ "model.layers.6.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
880
+ "model.layers.6.self_attn.q_layernorm.weight": "model-00001-of-00005.safetensors",
881
+ "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00005.safetensors",
882
+ "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00005.safetensors",
883
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
884
+ "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00005.safetensors",
885
+ "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00005.safetensors",
886
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
887
+ "model.layers.7.conv.conv.weight": "model-00001-of-00005.safetensors",
888
+ "model.layers.7.conv.in_proj.biases": "model-00001-of-00005.safetensors",
889
+ "model.layers.7.conv.in_proj.scales": "model-00001-of-00005.safetensors",
890
+ "model.layers.7.conv.in_proj.weight": "model-00001-of-00005.safetensors",
891
+ "model.layers.7.conv.out_proj.biases": "model-00001-of-00005.safetensors",
892
+ "model.layers.7.conv.out_proj.scales": "model-00001-of-00005.safetensors",
893
+ "model.layers.7.conv.out_proj.weight": "model-00001-of-00005.safetensors",
894
+ "model.layers.7.feed_forward.expert_bias": "model-00001-of-00005.safetensors",
895
+ "model.layers.7.feed_forward.gate.biases": "model-00001-of-00005.safetensors",
896
+ "model.layers.7.feed_forward.gate.scales": "model-00001-of-00005.safetensors",
897
+ "model.layers.7.feed_forward.gate.weight": "model-00001-of-00005.safetensors",
898
+ "model.layers.7.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00005.safetensors",
899
+ "model.layers.7.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00005.safetensors",
900
+ "model.layers.7.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00005.safetensors",
901
+ "model.layers.7.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00005.safetensors",
902
+ "model.layers.7.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00005.safetensors",
903
+ "model.layers.7.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
904
+ "model.layers.7.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00005.safetensors",
905
+ "model.layers.7.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00005.safetensors",
906
+ "model.layers.7.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00005.safetensors",
907
+ "model.layers.7.ffn_norm.weight": "model-00001-of-00005.safetensors",
908
+ "model.layers.7.operator_norm.weight": "model-00001-of-00005.safetensors",
909
+ "model.layers.8.conv.conv.weight": "model-00001-of-00005.safetensors",
910
+ "model.layers.8.conv.in_proj.biases": "model-00001-of-00005.safetensors",
911
+ "model.layers.8.conv.in_proj.scales": "model-00001-of-00005.safetensors",
912
+ "model.layers.8.conv.in_proj.weight": "model-00001-of-00005.safetensors",
913
+ "model.layers.8.conv.out_proj.biases": "model-00001-of-00005.safetensors",
914
+ "model.layers.8.conv.out_proj.scales": "model-00001-of-00005.safetensors",
915
+ "model.layers.8.conv.out_proj.weight": "model-00001-of-00005.safetensors",
916
+ "model.layers.8.feed_forward.expert_bias": "model-00001-of-00005.safetensors",
917
+ "model.layers.8.feed_forward.gate.biases": "model-00001-of-00005.safetensors",
918
+ "model.layers.8.feed_forward.gate.scales": "model-00001-of-00005.safetensors",
919
+ "model.layers.8.feed_forward.gate.weight": "model-00001-of-00005.safetensors",
920
+ "model.layers.8.feed_forward.switch_mlp.down_proj.biases": "model-00001-of-00005.safetensors",
921
+ "model.layers.8.feed_forward.switch_mlp.down_proj.scales": "model-00001-of-00005.safetensors",
922
+ "model.layers.8.feed_forward.switch_mlp.down_proj.weight": "model-00001-of-00005.safetensors",
923
+ "model.layers.8.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00005.safetensors",
924
+ "model.layers.8.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00005.safetensors",
925
+ "model.layers.8.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
926
+ "model.layers.8.feed_forward.switch_mlp.up_proj.biases": "model-00001-of-00005.safetensors",
927
+ "model.layers.8.feed_forward.switch_mlp.up_proj.scales": "model-00001-of-00005.safetensors",
928
+ "model.layers.8.feed_forward.switch_mlp.up_proj.weight": "model-00001-of-00005.safetensors",
929
+ "model.layers.8.ffn_norm.weight": "model-00001-of-00005.safetensors",
930
+ "model.layers.8.operator_norm.weight": "model-00001-of-00005.safetensors",
931
+ "model.layers.9.conv.conv.weight": "model-00001-of-00005.safetensors",
932
+ "model.layers.9.conv.in_proj.biases": "model-00001-of-00005.safetensors",
933
+ "model.layers.9.conv.in_proj.scales": "model-00001-of-00005.safetensors",
934
+ "model.layers.9.conv.in_proj.weight": "model-00001-of-00005.safetensors",
935
+ "model.layers.9.conv.out_proj.biases": "model-00001-of-00005.safetensors",
936
+ "model.layers.9.conv.out_proj.scales": "model-00001-of-00005.safetensors",
937
+ "model.layers.9.conv.out_proj.weight": "model-00001-of-00005.safetensors",
938
+ "model.layers.9.feed_forward.expert_bias": "model-00002-of-00005.safetensors",
939
+ "model.layers.9.feed_forward.gate.biases": "model-00001-of-00005.safetensors",
940
+ "model.layers.9.feed_forward.gate.scales": "model-00001-of-00005.safetensors",
941
+ "model.layers.9.feed_forward.gate.weight": "model-00001-of-00005.safetensors",
942
+ "model.layers.9.feed_forward.switch_mlp.down_proj.biases": "model-00002-of-00005.safetensors",
943
+ "model.layers.9.feed_forward.switch_mlp.down_proj.scales": "model-00002-of-00005.safetensors",
944
+ "model.layers.9.feed_forward.switch_mlp.down_proj.weight": "model-00002-of-00005.safetensors",
945
+ "model.layers.9.feed_forward.switch_mlp.gate_proj.biases": "model-00001-of-00005.safetensors",
946
+ "model.layers.9.feed_forward.switch_mlp.gate_proj.scales": "model-00001-of-00005.safetensors",
947
+ "model.layers.9.feed_forward.switch_mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
948
+ "model.layers.9.feed_forward.switch_mlp.up_proj.biases": "model-00002-of-00005.safetensors",
949
+ "model.layers.9.feed_forward.switch_mlp.up_proj.scales": "model-00002-of-00005.safetensors",
950
+ "model.layers.9.feed_forward.switch_mlp.up_proj.weight": "model-00002-of-00005.safetensors",
951
+ "model.layers.9.ffn_norm.weight": "model-00002-of-00005.safetensors",
952
+ "model.layers.9.operator_norm.weight": "model-00002-of-00005.safetensors"
953
+ }
954
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|startoftext|>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "<|im_end|>",
6
+ "extra_special_tokens": [],
7
+ "is_local": true,
8
+ "legacy": false,
9
+ "model_input_names": [
10
+ "input_ids",
11
+ "attention_mask"
12
+ ],
13
+ "model_max_length": 1000000000000000019884624838656,
14
+ "model_specific_special_tokens": {},
15
+ "pad_token": "<|pad|>",
16
+ "sp_model_kwargs": {},
17
+ "spaces_between_special_tokens": false,
18
+ "tokenizer_class": "TokenizersBackend",
19
+ "use_default_system_prompt": false,
20
+ "use_fast": true
21
+ }