Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "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.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "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.
+
+      "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
+      (an example is provided in the Appendix below).
+
+      "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.
+
+      "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."
+
+      "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.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, 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.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, 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.
+
+   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:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (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
+
+      (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.
+
+      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.
+
+   5. 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.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. 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.
+
+   8. 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.
+
+   9. 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.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 Alibaba Cloud
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

chat_template.jinja

@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

chipformer.json

@@ -0,0 +1,313 @@
+{
+ "layout": "rv1-tok",
+ "chip_token_offset": 248320,
+ "chip_vocab": 236469,
+ "chip_layers": 11,
+ "qwen_layers_from": 11,
+ "hidden": 3968,
+ "chip_dims_offset": 2560,
+ "ballast_dims": 62,
+ "circuit": {
+  "layers": 11,
+  "dims": 2919,
+  "heads": 103,
+  "ffn_units": 42199,
+  "max_units": 8149,
+  "max_heads": 16
+ },
+ "slots": 1266,
+ "muted": true,
+ "code_dims": [
+  2754,
+  2755,
+  2756,
+  2757,
+  2758,
+  2759,
+  2760,
+  2761,
+  2762,
+  2763,
+  2764,
+  2765,
+  2766,
+  2767,
+  2768,
+  2769,
+  2770,
+  2771,
+  2772,
+  2773,
+  2774
+ ],
+ "tau_dim": 2777,
+ "mu_dim": 2776,
+ "nfam": 5,
+ "npay": 16,
+ "tool_call": [
+  248058,
+  248059
+ ],
+ "printable": [
+  188,
+  189,
+  190,
+  191,
+  192,
+  193,
+  194,
+  195,
+  196,
+  197,
+  198,
+  199,
+  200,
+  201,
+  202,
+  203,
+  204,
+  205,
+  206,
+  207,
+  208,
+  209,
+  210,
+  211,
+  212,
+  213,
+  214,
+  215,
+  216,
+  217,
+  218,
+  219,
+  220,
+  0,
+  1,
+  2,
+  3,
+  4,
+  5,
+  6,
+  7,
+  8,
+  9,
+  10,
+  11,
+  12,
+  13,
+  14,
+  15,
+  16,
+  17,
+  18,
+  19,
+  20,
+  21,
+  22,
+  23,
+  24,
+  25,
+  26,
+  27,
+  28,
+  29,
+  30,
+  31,
+  32,
+  33,
+  34,
+  35,
+  36,
+  37,
+  38,
+  39,
+  40,
+  41,
+  42,
+  43,
+  44,
+  45,
+  46,
+  47,
+  48,
+  49,
+  50,
+  51,
+  52,
+  53,
+  54,
+  55,
+  56,
+  57,
+  58,
+  59,
+  60,
+  61,
+  62,
+  63,
+  64,
+  65,
+  66,
+  67,
+  68,
+  69,
+  70,
+  71,
+  72,
+  73,
+  74,
+  75,
+  76,
+  77,
+  78,
+  79,
+  80,
+  81,
+  82,
+  83,
+  84,
+  85,
+  86,
+  87,
+  88,
+  89,
+  90,
+  91,
+  92,
+  93,
+  221,
+  222,
+  223,
+  224,
+  225,
+  226,
+  227,
+  228,
+  229,
+  230,
+  231,
+  232,
+  233,
+  234,
+  235,
+  236,
+  237,
+  238,
+  239,
+  240,
+  241,
+  242,
+  243,
+  244,
+  245,
+  246,
+  247,
+  248,
+  249,
+  250,
+  251,
+  252,
+  253,
+  254,
+  94,
+  95,
+  96,
+  97,
+  98,
+  99,
+  100,
+  101,
+  102,
+  103,
+  104,
+  105,
+  255,
+  106,
+  107,
+  108,
+  109,
+  110,
+  111,
+  112,
+  113,
+  114,
+  115,
+  116,
+  117,
+  118,
+  119,
+  120,
+  121,
+  122,
+  123,
+  124,
+  125,
+  126,
+  127,
+  128,
+  129,
+  130,
+  131,
+  132,
+  133,
+  134,
+  135,
+  136,
+  137,
+  138,
+  139,
+  140,
+  141,
+  142,
+  143,
+  144,
+  145,
+  146,
+  147,
+  148,
+  149,
+  150,
+  151,
+  152,
+  153,
+  154,
+  155,
+  156,
+  157,
+  158,
+  159,
+  160,
+  161,
+  162,
+  163,
+  164,
+  165,
+  166,
+  167,
+  168,
+  169,
+  170,
+  171,
+  172,
+  173,
+  174,
+  175,
+  176,
+  177,
+  178,
+  179,
+  180,
+  181,
+  182,
+  183,
+  184,
+  185,
+  186,
+  187,
+  248066,
+  248067,
+  248068,
+  248069
+ ]
+}

config.json

@@ -0,0 +1,89 @@
+{
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_output_gate": true,
+  "dtype": "bfloat16",
+  "eos_token_id": 248044,
+  "head_dim": 256,
+  "hidden_act": "silu",
+  "hidden_size": 3968,
+  "initializer_range": 0.02,
+  "intermediate_size": 9216,
+  "layer_types": [
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention"
+  ],
+  "linear_conv_kernel_dim": 4,
+  "linear_key_head_dim": 128,
+  "linear_num_key_heads": 16,
+  "linear_num_value_heads": 32,
+  "linear_value_head_dim": 128,
+  "max_position_embeddings": 262144,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_5_text",
+  "mtp_num_hidden_layers": 0,
+  "mtp_use_dedicated_embeddings": false,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 43,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": true,
+  "use_cache": true,
+  "vocab_size": 484800,
+  "mamba_ssm_dtype": "float32",
+  "rope_parameters": {
+    "mrope_interleaved": true,
+    "mrope_section": [
+      11,
+      11,
+      10
+    ],
+    "rope_type": "default",
+    "rope_theta": 10000000,
+    "partial_rotary_factor": 0.25
+  },
+  "architectures": [
+    "Qwen3_5ForCausalLM"
+  ]
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "eos_token_id": [
+    248046,
+    248044
+  ],
+  "pad_token_id": 248044,
+  "do_sample": false
+}

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b18dec29bff5952daa474e2a43b0c3fd067a470febc89128f5f4135a4a6b0bf2
+size 3847372944

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c22ef1bca2df7b7d0833bcaa4bfc5e51a38184c4ce43844f83c5587e9a497e78
+size 2173322760

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f32ad4c3307f3b85533ad9fbcdeed7927f1554a06b4b502a89b3869ebefd2c0a
+size 2197122920

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbb004a2e51021c6fd7a7e0eaf3114f6ce59c6b232737c741e9fa5789bd264af
+size 2156489312

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2749c9fbc271d4ac73ad90171042187e39c895eb5e50b61db6cc6f128d93e80
+size 2205264744

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57e91fcd3133edd4464d356c4dfa93712a71661c7914cd996443d56322603123
+size 2148363592

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a456d0f75fe13769f2250f3b9c1af825d24047c6dd27f44ea793a00711a85c35
+size 2172166984

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d17b23975cd9f7f85652cc3db883ab70d55568a95e523d126371ed0414d22647
+size 1863934544

model.safetensors.index.json

@@ -0,0 +1,587 @@
+{
+  "metadata": {
+    "total_size": 18763963776
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.0.linear_attn.A_log": "model-00002-of-00008.safetensors",
+    "model.layers.0.linear_attn.conv1d.weight": "model-00002-of-00008.safetensors",
+    "model.layers.0.linear_attn.dt_bias": "model-00002-of-00008.safetensors",
+    "model.layers.0.linear_attn.in_proj_a.weight": "model-00002-of-00008.safetensors",
+    "model.layers.0.linear_attn.in_proj_b.weight": "model-00002-of-00008.safetensors",
+    "model.layers.0.linear_attn.in_proj_qkv.weight": "model-00002-of-00008.safetensors",
+    "model.layers.0.linear_attn.in_proj_z.weight": "model-00002-of-00008.safetensors",
+    "model.layers.0.linear_attn.norm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.0.linear_attn.out_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.1.linear_attn.A_log": "model-00002-of-00008.safetensors",
+    "model.layers.1.linear_attn.conv1d.weight": "model-00002-of-00008.safetensors",
+    "model.layers.1.linear_attn.dt_bias": "model-00002-of-00008.safetensors",
+    "model.layers.1.linear_attn.in_proj_a.weight": "model-00002-of-00008.safetensors",
+    "model.layers.1.linear_attn.in_proj_b.weight": "model-00002-of-00008.safetensors",
+    "model.layers.1.linear_attn.in_proj_qkv.weight": "model-00002-of-00008.safetensors",
+    "model.layers.1.linear_attn.in_proj_z.weight": "model-00002-of-00008.safetensors",
+    "model.layers.1.linear_attn.norm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.1.linear_attn.out_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.linear_attn.A_log": "model-00002-of-00008.safetensors",
+    "model.layers.10.linear_attn.conv1d.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.linear_attn.dt_bias": "model-00002-of-00008.safetensors",
+    "model.layers.10.linear_attn.in_proj_a.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.linear_attn.in_proj_b.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.linear_attn.in_proj_qkv.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.linear_attn.in_proj_z.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.linear_attn.norm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.linear_attn.out_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.11.linear_attn.A_log": "model-00002-of-00008.safetensors",
+    "model.layers.11.linear_attn.conv1d.weight": "model-00002-of-00008.safetensors",
+    "model.layers.11.linear_attn.dt_bias": "model-00002-of-00008.safetensors",
+    "model.layers.11.linear_attn.in_proj_a.weight": "model-00002-of-00008.safetensors",
+    "model.layers.11.linear_attn.in_proj_b.weight": "model-00002-of-00008.safetensors",
+    "model.layers.11.linear_attn.in_proj_qkv.weight": "model-00002-of-00008.safetensors",
+    "model.layers.11.linear_attn.in_proj_z.weight": "model-00002-of-00008.safetensors",
+    "model.layers.11.linear_attn.norm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.11.linear_attn.out_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.12.linear_attn.A_log": "model-00002-of-00008.safetensors",
+    "model.layers.12.linear_attn.conv1d.weight": "model-00002-of-00008.safetensors",
+    "model.layers.12.linear_attn.dt_bias": "model-00002-of-00008.safetensors",
+    "model.layers.12.linear_attn.in_proj_a.weight": "model-00002-of-00008.safetensors",
+    "model.layers.12.linear_attn.in_proj_b.weight": "model-00002-of-00008.safetensors",
+    "model.layers.12.linear_attn.in_proj_qkv.weight": "model-00002-of-00008.safetensors",
+    "model.layers.12.linear_attn.in_proj_z.weight": "model-00002-of-00008.safetensors",
+    "model.layers.12.linear_attn.norm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.12.linear_attn.out_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.13.linear_attn.A_log": "model-00002-of-00008.safetensors",
+    "model.layers.13.linear_attn.conv1d.weight": "model-00002-of-00008.safetensors",
+    "model.layers.13.linear_attn.dt_bias": "model-00002-of-00008.safetensors",
+    "model.layers.13.linear_attn.in_proj_a.weight": "model-00002-of-00008.safetensors",
+    "model.layers.13.linear_attn.in_proj_b.weight": "model-00002-of-00008.safetensors",
+    "model.layers.13.linear_attn.in_proj_qkv.weight": "model-00002-of-00008.safetensors",
+    "model.layers.13.linear_attn.in_proj_z.weight": "model-00002-of-00008.safetensors",
+    "model.layers.13.linear_attn.norm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.13.linear_attn.out_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.linear_attn.A_log": "model-00003-of-00008.safetensors",
+    "model.layers.15.linear_attn.conv1d.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.linear_attn.dt_bias": "model-00003-of-00008.safetensors",
+    "model.layers.15.linear_attn.in_proj_a.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.linear_attn.in_proj_b.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.linear_attn.in_proj_qkv.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.linear_attn.in_proj_z.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.linear_attn.norm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.linear_attn.out_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.linear_attn.A_log": "model-00003-of-00008.safetensors",
+    "model.layers.16.linear_attn.conv1d.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.linear_attn.dt_bias": "model-00003-of-00008.safetensors",
+    "model.layers.16.linear_attn.in_proj_a.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.linear_attn.in_proj_b.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.linear_attn.in_proj_qkv.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.linear_attn.in_proj_z.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.linear_attn.norm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.linear_attn.out_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.linear_attn.A_log": "model-00003-of-00008.safetensors",
+    "model.layers.17.linear_attn.conv1d.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.linear_attn.dt_bias": "model-00003-of-00008.safetensors",
+    "model.layers.17.linear_attn.in_proj_a.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.linear_attn.in_proj_b.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.linear_attn.in_proj_qkv.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.linear_attn.in_proj_z.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.linear_attn.norm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.linear_attn.out_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.19.linear_attn.A_log": "model-00003-of-00008.safetensors",
+    "model.layers.19.linear_attn.conv1d.weight": "model-00003-of-00008.safetensors",
+    "model.layers.19.linear_attn.dt_bias": "model-00003-of-00008.safetensors",
+    "model.layers.19.linear_attn.in_proj_a.weight": "model-00003-of-00008.safetensors",
+    "model.layers.19.linear_attn.in_proj_b.weight": "model-00003-of-00008.safetensors",
+    "model.layers.19.linear_attn.in_proj_qkv.weight": "model-00003-of-00008.safetensors",
+    "model.layers.19.linear_attn.in_proj_z.weight": "model-00003-of-00008.safetensors",
+    "model.layers.19.linear_attn.norm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.19.linear_attn.out_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.2.linear_attn.A_log": "model-00003-of-00008.safetensors",
+    "model.layers.2.linear_attn.conv1d.weight": "model-00003-of-00008.safetensors",
+    "model.layers.2.linear_attn.dt_bias": "model-00003-of-00008.safetensors",
+    "model.layers.2.linear_attn.in_proj_a.weight": "model-00003-of-00008.safetensors",
+    "model.layers.2.linear_attn.in_proj_b.weight": "model-00003-of-00008.safetensors",
+    "model.layers.2.linear_attn.in_proj_qkv.weight": "model-00003-of-00008.safetensors",
+    "model.layers.2.linear_attn.in_proj_z.weight": "model-00003-of-00008.safetensors",
+    "model.layers.2.linear_attn.norm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.2.linear_attn.out_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.linear_attn.A_log": "model-00004-of-00008.safetensors",
+    "model.layers.20.linear_attn.conv1d.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.linear_attn.dt_bias": "model-00004-of-00008.safetensors",
+    "model.layers.20.linear_attn.in_proj_a.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.linear_attn.in_proj_b.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.linear_attn.in_proj_qkv.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.linear_attn.in_proj_z.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.linear_attn.norm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.linear_attn.out_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.linear_attn.A_log": "model-00004-of-00008.safetensors",
+    "model.layers.21.linear_attn.conv1d.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.linear_attn.dt_bias": "model-00004-of-00008.safetensors",
+    "model.layers.21.linear_attn.in_proj_a.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.linear_attn.in_proj_b.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.linear_attn.in_proj_qkv.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.linear_attn.in_proj_z.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.linear_attn.norm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.linear_attn.out_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.linear_attn.A_log": "model-00004-of-00008.safetensors",
+    "model.layers.23.linear_attn.conv1d.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.linear_attn.dt_bias": "model-00004-of-00008.safetensors",
+    "model.layers.23.linear_attn.in_proj_a.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.linear_attn.in_proj_b.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.linear_attn.in_proj_qkv.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.linear_attn.in_proj_z.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.linear_attn.norm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.linear_attn.out_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.24.linear_attn.A_log": "model-00004-of-00008.safetensors",
+    "model.layers.24.linear_attn.conv1d.weight": "model-00004-of-00008.safetensors",
+    "model.layers.24.linear_attn.dt_bias": "model-00004-of-00008.safetensors",
+    "model.layers.24.linear_attn.in_proj_a.weight": "model-00004-of-00008.safetensors",
+    "model.layers.24.linear_attn.in_proj_b.weight": "model-00004-of-00008.safetensors",
+    "model.layers.24.linear_attn.in_proj_qkv.weight": "model-00004-of-00008.safetensors",
+    "model.layers.24.linear_attn.in_proj_z.weight": "model-00004-of-00008.safetensors",
+    "model.layers.24.linear_attn.norm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.24.linear_attn.out_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.25.linear_attn.A_log": "model-00004-of-00008.safetensors",
+    "model.layers.25.linear_attn.conv1d.weight": "model-00004-of-00008.safetensors",
+    "model.layers.25.linear_attn.dt_bias": "model-00004-of-00008.safetensors",
+    "model.layers.25.linear_attn.in_proj_a.weight": "model-00004-of-00008.safetensors",
+    "model.layers.25.linear_attn.in_proj_b.weight": "model-00004-of-00008.safetensors",
+    "model.layers.25.linear_attn.in_proj_qkv.weight": "model-00004-of-00008.safetensors",
+    "model.layers.25.linear_attn.in_proj_z.weight": "model-00004-of-00008.safetensors",
+    "model.layers.25.linear_attn.norm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.25.linear_attn.out_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.linear_attn.A_log": "model-00005-of-00008.safetensors",
+    "model.layers.27.linear_attn.conv1d.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.linear_attn.dt_bias": "model-00005-of-00008.safetensors",
+    "model.layers.27.linear_attn.in_proj_a.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.linear_attn.in_proj_b.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.linear_attn.in_proj_qkv.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.linear_attn.in_proj_z.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.linear_attn.norm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.linear_attn.out_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.28.linear_attn.A_log": "model-00005-of-00008.safetensors",
+    "model.layers.28.linear_attn.conv1d.weight": "model-00005-of-00008.safetensors",
+    "model.layers.28.linear_attn.dt_bias": "model-00005-of-00008.safetensors",
+    "model.layers.28.linear_attn.in_proj_a.weight": "model-00005-of-00008.safetensors",
+    "model.layers.28.linear_attn.in_proj_b.weight": "model-00005-of-00008.safetensors",
+    "model.layers.28.linear_attn.in_proj_qkv.weight": "model-00005-of-00008.safetensors",
+    "model.layers.28.linear_attn.in_proj_z.weight": "model-00005-of-00008.safetensors",
+    "model.layers.28.linear_attn.norm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.28.linear_attn.out_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.29.linear_attn.A_log": "model-00005-of-00008.safetensors",
+    "model.layers.29.linear_attn.conv1d.weight": "model-00005-of-00008.safetensors",
+    "model.layers.29.linear_attn.dt_bias": "model-00005-of-00008.safetensors",
+    "model.layers.29.linear_attn.in_proj_a.weight": "model-00005-of-00008.safetensors",
+    "model.layers.29.linear_attn.in_proj_b.weight": "model-00005-of-00008.safetensors",
+    "model.layers.29.linear_attn.in_proj_qkv.weight": "model-00005-of-00008.safetensors",
+    "model.layers.29.linear_attn.in_proj_z.weight": "model-00005-of-00008.safetensors",
+    "model.layers.29.linear_attn.norm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.29.linear_attn.out_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.3.linear_attn.A_log": "model-00005-of-00008.safetensors",
+    "model.layers.3.linear_attn.conv1d.weight": "model-00005-of-00008.safetensors",
+    "model.layers.3.linear_attn.dt_bias": "model-00005-of-00008.safetensors",
+    "model.layers.3.linear_attn.in_proj_a.weight": "model-00005-of-00008.safetensors",
+    "model.layers.3.linear_attn.in_proj_b.weight": "model-00005-of-00008.safetensors",
+    "model.layers.3.linear_attn.in_proj_qkv.weight": "model-00005-of-00008.safetensors",
+    "model.layers.3.linear_attn.in_proj_z.weight": "model-00005-of-00008.safetensors",
+    "model.layers.3.linear_attn.norm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.3.linear_attn.out_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.31.linear_attn.A_log": "model-00005-of-00008.safetensors",
+    "model.layers.31.linear_attn.conv1d.weight": "model-00005-of-00008.safetensors",
+    "model.layers.31.linear_attn.dt_bias": "model-00005-of-00008.safetensors",
+    "model.layers.31.linear_attn.in_proj_a.weight": "model-00005-of-00008.safetensors",
+    "model.layers.31.linear_attn.in_proj_b.weight": "model-00005-of-00008.safetensors",
+    "model.layers.31.linear_attn.in_proj_qkv.weight": "model-00005-of-00008.safetensors",
+    "model.layers.31.linear_attn.in_proj_z.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.linear_attn.norm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.linear_attn.out_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.linear_attn.A_log": "model-00006-of-00008.safetensors",
+    "model.layers.32.linear_attn.conv1d.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.linear_attn.dt_bias": "model-00006-of-00008.safetensors",
+    "model.layers.32.linear_attn.in_proj_a.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.linear_attn.in_proj_b.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.linear_attn.in_proj_qkv.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.linear_attn.in_proj_z.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.linear_attn.norm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.linear_attn.out_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.linear_attn.A_log": "model-00006-of-00008.safetensors",
+    "model.layers.33.linear_attn.conv1d.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.linear_attn.dt_bias": "model-00006-of-00008.safetensors",
+    "model.layers.33.linear_attn.in_proj_a.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.linear_attn.in_proj_b.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.linear_attn.in_proj_qkv.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.linear_attn.in_proj_z.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.linear_attn.norm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.linear_attn.out_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.35.linear_attn.A_log": "model-00006-of-00008.safetensors",
+    "model.layers.35.linear_attn.conv1d.weight": "model-00006-of-00008.safetensors",
+    "model.layers.35.linear_attn.dt_bias": "model-00006-of-00008.safetensors",
+    "model.layers.35.linear_attn.in_proj_a.weight": "model-00006-of-00008.safetensors",
+    "model.layers.35.linear_attn.in_proj_b.weight": "model-00006-of-00008.safetensors",
+    "model.layers.35.linear_attn.in_proj_qkv.weight": "model-00006-of-00008.safetensors",
+    "model.layers.35.linear_attn.in_proj_z.weight": "model-00006-of-00008.safetensors",
+    "model.layers.35.linear_attn.norm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.35.linear_attn.out_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.36.linear_attn.A_log": "model-00006-of-00008.safetensors",
+    "model.layers.36.linear_attn.conv1d.weight": "model-00006-of-00008.safetensors",
+    "model.layers.36.linear_attn.dt_bias": "model-00006-of-00008.safetensors",
+    "model.layers.36.linear_attn.in_proj_a.weight": "model-00006-of-00008.safetensors",
+    "model.layers.36.linear_attn.in_proj_b.weight": "model-00006-of-00008.safetensors",
+    "model.layers.36.linear_attn.in_proj_qkv.weight": "model-00006-of-00008.safetensors",
+    "model.layers.36.linear_attn.in_proj_z.weight": "model-00006-of-00008.safetensors",
+    "model.layers.36.linear_attn.norm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.36.linear_attn.out_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.37.linear_attn.A_log": "model-00006-of-00008.safetensors",
+    "model.layers.37.linear_attn.conv1d.weight": "model-00006-of-00008.safetensors",
+    "model.layers.37.linear_attn.dt_bias": "model-00006-of-00008.safetensors",
+    "model.layers.37.linear_attn.in_proj_a.weight": "model-00006-of-00008.safetensors",
+    "model.layers.37.linear_attn.in_proj_b.weight": "model-00006-of-00008.safetensors",
+    "model.layers.37.linear_attn.in_proj_qkv.weight": "model-00006-of-00008.safetensors",
+    "model.layers.37.linear_attn.in_proj_z.weight": "model-00006-of-00008.safetensors",
+    "model.layers.37.linear_attn.norm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.37.linear_attn.out_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.self_attn.k_norm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.self_attn.q_norm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.39.linear_attn.A_log": "model-00007-of-00008.safetensors",
+    "model.layers.39.linear_attn.conv1d.weight": "model-00007-of-00008.safetensors",
+    "model.layers.39.linear_attn.dt_bias": "model-00007-of-00008.safetensors",
+    "model.layers.39.linear_attn.in_proj_a.weight": "model-00007-of-00008.safetensors",
+    "model.layers.39.linear_attn.in_proj_b.weight": "model-00007-of-00008.safetensors",
+    "model.layers.39.linear_attn.in_proj_qkv.weight": "model-00007-of-00008.safetensors",
+    "model.layers.39.linear_attn.in_proj_z.weight": "model-00007-of-00008.safetensors",
+    "model.layers.39.linear_attn.norm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.39.linear_attn.out_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.4.linear_attn.A_log": "model-00007-of-00008.safetensors",
+    "model.layers.4.linear_attn.conv1d.weight": "model-00007-of-00008.safetensors",
+    "model.layers.4.linear_attn.dt_bias": "model-00007-of-00008.safetensors",
+    "model.layers.4.linear_attn.in_proj_a.weight": "model-00007-of-00008.safetensors",
+    "model.layers.4.linear_attn.in_proj_b.weight": "model-00007-of-00008.safetensors",
+    "model.layers.4.linear_attn.in_proj_qkv.weight": "model-00007-of-00008.safetensors",
+    "model.layers.4.linear_attn.in_proj_z.weight": "model-00007-of-00008.safetensors",
+    "model.layers.4.linear_attn.norm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.4.linear_attn.out_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.40.linear_attn.A_log": "model-00007-of-00008.safetensors",
+    "model.layers.40.linear_attn.conv1d.weight": "model-00007-of-00008.safetensors",
+    "model.layers.40.linear_attn.dt_bias": "model-00007-of-00008.safetensors",
+    "model.layers.40.linear_attn.in_proj_a.weight": "model-00007-of-00008.safetensors",
+    "model.layers.40.linear_attn.in_proj_b.weight": "model-00007-of-00008.safetensors",
+    "model.layers.40.linear_attn.in_proj_qkv.weight": "model-00007-of-00008.safetensors",
+    "model.layers.40.linear_attn.in_proj_z.weight": "model-00007-of-00008.safetensors",
+    "model.layers.40.linear_attn.norm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.40.linear_attn.out_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.41.linear_attn.A_log": "model-00007-of-00008.safetensors",
+    "model.layers.41.linear_attn.conv1d.weight": "model-00007-of-00008.safetensors",
+    "model.layers.41.linear_attn.dt_bias": "model-00007-of-00008.safetensors",
+    "model.layers.41.linear_attn.in_proj_a.weight": "model-00007-of-00008.safetensors",
+    "model.layers.41.linear_attn.in_proj_b.weight": "model-00007-of-00008.safetensors",
+    "model.layers.41.linear_attn.in_proj_qkv.weight": "model-00007-of-00008.safetensors",
+    "model.layers.41.linear_attn.in_proj_z.weight": "model-00007-of-00008.safetensors",
+    "model.layers.41.linear_attn.norm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.41.linear_attn.out_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.42.self_attn.k_norm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.42.self_attn.q_norm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.5.linear_attn.A_log": "model-00008-of-00008.safetensors",
+    "model.layers.5.linear_attn.conv1d.weight": "model-00008-of-00008.safetensors",
+    "model.layers.5.linear_attn.dt_bias": "model-00008-of-00008.safetensors",
+    "model.layers.5.linear_attn.in_proj_a.weight": "model-00008-of-00008.safetensors",
+    "model.layers.5.linear_attn.in_proj_b.weight": "model-00008-of-00008.safetensors",
+    "model.layers.5.linear_attn.in_proj_qkv.weight": "model-00008-of-00008.safetensors",
+    "model.layers.5.linear_attn.in_proj_z.weight": "model-00008-of-00008.safetensors",
+    "model.layers.5.linear_attn.norm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.5.linear_attn.out_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.6.linear_attn.A_log": "model-00008-of-00008.safetensors",
+    "model.layers.6.linear_attn.conv1d.weight": "model-00008-of-00008.safetensors",
+    "model.layers.6.linear_attn.dt_bias": "model-00008-of-00008.safetensors",
+    "model.layers.6.linear_attn.in_proj_a.weight": "model-00008-of-00008.safetensors",
+    "model.layers.6.linear_attn.in_proj_b.weight": "model-00008-of-00008.safetensors",
+    "model.layers.6.linear_attn.in_proj_qkv.weight": "model-00008-of-00008.safetensors",
+    "model.layers.6.linear_attn.in_proj_z.weight": "model-00008-of-00008.safetensors",
+    "model.layers.6.linear_attn.norm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.6.linear_attn.out_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.7.linear_attn.A_log": "model-00008-of-00008.safetensors",
+    "model.layers.7.linear_attn.conv1d.weight": "model-00008-of-00008.safetensors",
+    "model.layers.7.linear_attn.dt_bias": "model-00008-of-00008.safetensors",
+    "model.layers.7.linear_attn.in_proj_a.weight": "model-00008-of-00008.safetensors",
+    "model.layers.7.linear_attn.in_proj_b.weight": "model-00008-of-00008.safetensors",
+    "model.layers.7.linear_attn.in_proj_qkv.weight": "model-00008-of-00008.safetensors",
+    "model.layers.7.linear_attn.in_proj_z.weight": "model-00008-of-00008.safetensors",
+    "model.layers.7.linear_attn.norm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.7.linear_attn.out_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.8.linear_attn.A_log": "model-00008-of-00008.safetensors",
+    "model.layers.8.linear_attn.conv1d.weight": "model-00008-of-00008.safetensors",
+    "model.layers.8.linear_attn.dt_bias": "model-00008-of-00008.safetensors",
+    "model.layers.8.linear_attn.in_proj_a.weight": "model-00008-of-00008.safetensors",
+    "model.layers.8.linear_attn.in_proj_b.weight": "model-00008-of-00008.safetensors",
+    "model.layers.8.linear_attn.in_proj_qkv.weight": "model-00008-of-00008.safetensors",
+    "model.layers.8.linear_attn.in_proj_z.weight": "model-00008-of-00008.safetensors",
+    "model.layers.8.linear_attn.norm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.8.linear_attn.out_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.9.linear_attn.A_log": "model-00008-of-00008.safetensors",
+    "model.layers.9.linear_attn.conv1d.weight": "model-00008-of-00008.safetensors",
+    "model.layers.9.linear_attn.dt_bias": "model-00008-of-00008.safetensors",
+    "model.layers.9.linear_attn.in_proj_a.weight": "model-00008-of-00008.safetensors",
+    "model.layers.9.linear_attn.in_proj_b.weight": "model-00008-of-00008.safetensors",
+    "model.layers.9.linear_attn.in_proj_qkv.weight": "model-00008-of-00008.safetensors",
+    "model.layers.9.linear_attn.in_proj_z.weight": "model-00008-of-00008.safetensors",
+    "model.layers.9.linear_attn.norm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.9.linear_attn.out_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.norm.weight": "model-00008-of-00008.safetensors"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dfe6de842131815aa46c5371b6427aa124d07c1a210a25f2a3e1347d69f19ca
+size 65204715

tokenizer_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f186292955c88c05a3ed3de09976b766591f3baf3a08711def652caf5f51774b
+size 42863392