model upload

chat_template.jinja

@@ -0,0 +1,114 @@
+{%- set tools_system_message_prefix = 'You are a helpful assistant with access to the following tools. You may call one or more tools to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>'  %}
+{%- set tools_system_message_suffix = '\n</tools>\n\nFor each tool call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.' %}
+{%- set documents_system_message_prefix = 'You are a helpful assistant with access to the following documents. You may use one or more documents to assist with the user query.\n\nYou are given a list of documents within <documents></documents> XML tags:\n<documents>' %}
+{%- set documents_system_message_suffix = '\n</documents>\n\nWrite the response to the user\'s input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.' %}
+{%- if available_tools is defined and available_tools %}
+    {%- set tools = available_tools %}
+{%- endif %}
+{%- set ns = namespace(tools_system_message=tools_system_message_prefix,
+                       documents_system_message=documents_system_message_prefix,
+                       system_message=''
+                       ) %}
+{%- if tools %}
+    {%- for tool in tools %}
+        {%- set ns.tools_system_message = ns.tools_system_message + '\n' + (tool | tojson) %}
+    {%- endfor %}
+    {%- set ns.tools_system_message = ns.tools_system_message + tools_system_message_suffix %}
+{%- else %}
+    {%- set ns.tools_system_message = '' %}
+{%- endif %}
+{%- if documents %}
+    {%- for document in documents %}
+        {%- set ns.documents_system_message = ns.documents_system_message + '\n' + (document | tojson) %}
+    {%- endfor %}
+    {%- set ns.documents_system_message = ns.documents_system_message + documents_system_message_suffix %}
+{%- else %}
+    {%- set ns.documents_system_message = '' %}
+{%- endif %}
+{%- if messages[0].role == 'system' %}
+    {%- if messages[0].content is string %}
+        {%- set ns.system_message = messages[0].content %}
+    {%- elif messages[0].content is iterable %}
+        {%- for entry in messages[0].content %}
+            {%- if entry.type== 'text' %}
+                {%- if ns.system_message != '' %}
+                    {%- set ns.system_message = ns.system_message + '\n' %}
+                {%- endif %}
+                {%- set ns.system_message = ns.system_message + entry.text %}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+    {%- if tools and documents %}
+        {%- set ns.system_message = ns.system_message + '\n\n' +  ns.tools_system_message + '\n\n' + ns.documents_system_message %}
+    {%- elif tools %}
+        {%- set ns.system_message = ns.system_message + '\n\n' + ns.tools_system_message %}
+    {%- elif documents %}
+        {%- set ns.system_message = ns.system_message + '\n\n' + ns.documents_system_message %}
+    {%- endif %}
+{%- else %}
+    {%- if tools and documents %}
+        {%- set ns.system_message = ns.tools_system_message + '\n\n' + ns.documents_system_message  %}
+    {%- elif tools %}
+        {%- set ns.system_message = ns.tools_system_message %}
+    {%- elif documents %}
+        {%- set ns.system_message = ns.documents_system_message %}
+    {%- endif %}
+{%- endif %}
+{%- if ns.system_message %}
+    {{- '<|start_of_role|>system<|end_of_role|>' + ns.system_message + '<|end_of_text|>\n' }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = namespace(val='') %}
+    {%- if message.content is string %}
+        {%- set content.val = message.content %}
+    {%- else %}
+        {%- if message.content is iterable %}
+            {%- for entry in message.content %}
+                {%- if entry.type== 'text' %}
+                    {%- if content.val != '' %}
+                        {%- set content.val = content.val + '\n' %}
+                    {%- endif %}
+                    {%- set content.val = content.val + entry.text %}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+    {%- endif %}
+    {%- if (message.role == 'user') or (message.role == 'system' and not loop.first) %}
+        {{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val + '<|end_of_text|>\n' }}
+    {%- elif message.role == 'assistant' %}
+        {{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val }}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content.val) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|end_of_text|>\n' }}
+    {%- elif message.role == 'tool' %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != 'tool') %}
+            {{- '<|start_of_role|>user<|end_of_role|>' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content.val }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != 'tool') %}
+            {{- '<|end_of_text|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_of_role|>assistant<|end_of_role|>' }}
+{%- endif %}

config.json

@@ -0,0 +1,89 @@
+{
+  "architectures": [
+    "GraniteMoeHybridForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_multiplier": 0.0078125,
+  "bos_token_id": 100257,
+  "embedding_multiplier": 12,
+  "eos_token_id": 100257,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.1,
+  "intermediate_size": 768,
+  "layer_types": [
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "attention",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "attention",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "attention",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba",
+    "attention",
+    "mamba",
+    "mamba",
+    "mamba",
+    "mamba"
+  ],
+  "logits_scaling": 16,
+  "mamba_chunk_size": 256,
+  "mamba_conv_bias": true,
+  "mamba_d_conv": 4,
+  "mamba_d_head": 64,
+  "mamba_d_state": 128,
+  "mamba_expand": 2,
+  "mamba_n_groups": 1,
+  "mamba_n_heads": 128,
+  "mamba_proj_bias": false,
+  "max_position_embeddings": 131072,
+  "model_type": "granitemoehybrid",
+  "normalization_function": "rmsnorm",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 10,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "num_local_experts": 72,
+  "output_router_logits": false,
+  "pad_token_id": 100256,
+  "position_embedding_type": "nope",
+  "residual_multiplier": 0.22,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "router_aux_loss_coef": 0.0,
+  "shared_intermediate_size": 1536,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.56.0",
+  "use_cache": true,
+  "vocab_size": 100352
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 100257,
+  "eos_token_id": 100257,
+  "pad_token_id": 100256,
+  "transformers_version": "4.56.0"
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f45359dac7e0fbffde4f4261d9959f86113e2347ef90e75e9b47f628c969ed38
+size 4931823752

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10586e2ebd97b828d2ddbba49f9bc066d10cddf71a352f177e09491b5c891f5d
+size 4805655352

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b13bb3c47222bbbedda637125eae5300fd102bf4a9536313e6e736b2e37de02
+size 4684967104

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9febd93455f138d2b08088131901a7b772e4a5c7b2a4c6cb73c524ed7b2a638c
+size 4805655392

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0b86c90323a9e80b229e99e727995d27e8d3d717cd20c0b1fbe7f09f036679e
+size 4805655400

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07e746cdc60458973fbca6e2bbe14cf86990b04082b8020eb5fde24757566113
+size 4684967136

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e99acbbdcba299f93b0b0b42ba9519626f086bed34593dbcc36b513195bf48d7
+size 4805655400

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9bde838b687e90aeb80d62cd35080cfbd8cb7c366e15601a4e058a348f1baac
+size 4805655400

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06afd739e8c459b22d09dde380949ac29bb3efa008e932bd49496fc0863a120f
+size 4684967136

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df18281f1f1e1ee2f0a2406ee5f18dba3c82127572b0ec61e995cb3f5f99bb13
+size 4805655400

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15dd3482b3bb3ba2f498572ac370a15c8c9c59bfcc3c1fa0a730c133a03b9ea6
+size 4805655400

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:480b31305085ca70d6ceaf7294a38b008395a0466527333043a8daf42643536d
+size 4805655400

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8e8cbbe40341a49618ec39c2f657c4ee88f82beed252b157c55d97036b7b4ef
+size 4684967144

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4bc589e873c34c93586f5ce84446f0cee838ddd4e847493a618868815d8a8cb
+size 2297808752

model.safetensors.index.json

@@ -0,0 +1,594 @@
+{
+  "metadata": {
+    "total_parameters": 0,
+    "total_size": 64414675968
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.block_sparse_moe.input_linear.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.block_sparse_moe.output_linear.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.block_sparse_moe.router.layer.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mamba.A_log": "model-00001-of-00014.safetensors",
+    "model.layers.0.mamba.D": "model-00001-of-00014.safetensors",
+    "model.layers.0.mamba.conv1d.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.mamba.conv1d.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mamba.dt_bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.mamba.in_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mamba.norm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mamba.out_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.shared_mlp.input_linear.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.shared_mlp.output_linear.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.block_sparse_moe.input_linear.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.block_sparse_moe.output_linear.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.block_sparse_moe.router.layer.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mamba.A_log": "model-00001-of-00014.safetensors",
+    "model.layers.1.mamba.D": "model-00001-of-00014.safetensors",
+    "model.layers.1.mamba.conv1d.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.mamba.conv1d.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mamba.dt_bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.mamba.in_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mamba.norm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mamba.out_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.shared_mlp.input_linear.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.shared_mlp.output_linear.weight": "model-00001-of-00014.safetensors",
+    "model.layers.10.block_sparse_moe.input_linear.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.block_sparse_moe.output_linear.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.block_sparse_moe.router.layer.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.mamba.A_log": "model-00004-of-00014.safetensors",
+    "model.layers.10.mamba.D": "model-00004-of-00014.safetensors",
+    "model.layers.10.mamba.conv1d.bias": "model-00004-of-00014.safetensors",
+    "model.layers.10.mamba.conv1d.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.mamba.dt_bias": "model-00004-of-00014.safetensors",
+    "model.layers.10.mamba.in_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.mamba.norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.mamba.out_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.shared_mlp.input_linear.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.shared_mlp.output_linear.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.block_sparse_moe.input_linear.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.block_sparse_moe.output_linear.weight": "model-00005-of-00014.safetensors",
+    "model.layers.11.block_sparse_moe.router.layer.weight": "model-00005-of-00014.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.11.mamba.A_log": "model-00005-of-00014.safetensors",
+    "model.layers.11.mamba.D": "model-00005-of-00014.safetensors",
+    "model.layers.11.mamba.conv1d.bias": "model-00005-of-00014.safetensors",
+    "model.layers.11.mamba.conv1d.weight": "model-00005-of-00014.safetensors",
+    "model.layers.11.mamba.dt_bias": "model-00005-of-00014.safetensors",
+    "model.layers.11.mamba.in_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.11.mamba.norm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.11.mamba.out_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.11.shared_mlp.input_linear.weight": "model-00005-of-00014.safetensors",
+    "model.layers.11.shared_mlp.output_linear.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.block_sparse_moe.input_linear.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.block_sparse_moe.output_linear.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.block_sparse_moe.router.layer.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.mamba.A_log": "model-00005-of-00014.safetensors",
+    "model.layers.12.mamba.D": "model-00005-of-00014.safetensors",
+    "model.layers.12.mamba.conv1d.bias": "model-00005-of-00014.safetensors",
+    "model.layers.12.mamba.conv1d.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.mamba.dt_bias": "model-00005-of-00014.safetensors",
+    "model.layers.12.mamba.in_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.mamba.norm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.mamba.out_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.shared_mlp.input_linear.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.shared_mlp.output_linear.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.block_sparse_moe.input_linear.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.block_sparse_moe.output_linear.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.block_sparse_moe.router.layer.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.mamba.A_log": "model-00005-of-00014.safetensors",
+    "model.layers.13.mamba.D": "model-00005-of-00014.safetensors",
+    "model.layers.13.mamba.conv1d.bias": "model-00005-of-00014.safetensors",
+    "model.layers.13.mamba.conv1d.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.mamba.dt_bias": "model-00005-of-00014.safetensors",
+    "model.layers.13.mamba.in_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.mamba.norm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.mamba.out_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.shared_mlp.input_linear.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.shared_mlp.output_linear.weight": "model-00005-of-00014.safetensors",
+    "model.layers.14.block_sparse_moe.input_linear.weight": "model-00005-of-00014.safetensors",
+    "model.layers.14.block_sparse_moe.output_linear.weight": "model-00006-of-00014.safetensors",
+    "model.layers.14.block_sparse_moe.router.layer.weight": "model-00006-of-00014.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.14.mamba.A_log": "model-00006-of-00014.safetensors",
+    "model.layers.14.mamba.D": "model-00006-of-00014.safetensors",
+    "model.layers.14.mamba.conv1d.bias": "model-00006-of-00014.safetensors",
+    "model.layers.14.mamba.conv1d.weight": "model-00006-of-00014.safetensors",
+    "model.layers.14.mamba.dt_bias": "model-00006-of-00014.safetensors",
+    "model.layers.14.mamba.in_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.14.mamba.norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.14.mamba.out_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.14.shared_mlp.input_linear.weight": "model-00006-of-00014.safetensors",
+    "model.layers.14.shared_mlp.output_linear.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.block_sparse_moe.input_linear.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.block_sparse_moe.output_linear.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.block_sparse_moe.router.layer.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.shared_mlp.input_linear.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.shared_mlp.output_linear.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.block_sparse_moe.input_linear.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.block_sparse_moe.output_linear.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.block_sparse_moe.router.layer.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.mamba.A_log": "model-00006-of-00014.safetensors",
+    "model.layers.16.mamba.D": "model-00006-of-00014.safetensors",
+    "model.layers.16.mamba.conv1d.bias": "model-00006-of-00014.safetensors",
+    "model.layers.16.mamba.conv1d.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.mamba.dt_bias": "model-00006-of-00014.safetensors",
+    "model.layers.16.mamba.in_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.mamba.norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.mamba.out_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.shared_mlp.input_linear.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.shared_mlp.output_linear.weight": "model-00006-of-00014.safetensors",
+    "model.layers.17.block_sparse_moe.input_linear.weight": "model-00006-of-00014.safetensors",
+    "model.layers.17.block_sparse_moe.output_linear.weight": "model-00007-of-00014.safetensors",
+    "model.layers.17.block_sparse_moe.router.layer.weight": "model-00007-of-00014.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.17.mamba.A_log": "model-00007-of-00014.safetensors",
+    "model.layers.17.mamba.D": "model-00007-of-00014.safetensors",
+    "model.layers.17.mamba.conv1d.bias": "model-00007-of-00014.safetensors",
+    "model.layers.17.mamba.conv1d.weight": "model-00007-of-00014.safetensors",
+    "model.layers.17.mamba.dt_bias": "model-00007-of-00014.safetensors",
+    "model.layers.17.mamba.in_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.17.mamba.norm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.17.mamba.out_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.17.shared_mlp.input_linear.weight": "model-00007-of-00014.safetensors",
+    "model.layers.17.shared_mlp.output_linear.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.block_sparse_moe.input_linear.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.block_sparse_moe.output_linear.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.block_sparse_moe.router.layer.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.mamba.A_log": "model-00007-of-00014.safetensors",
+    "model.layers.18.mamba.D": "model-00007-of-00014.safetensors",
+    "model.layers.18.mamba.conv1d.bias": "model-00007-of-00014.safetensors",
+    "model.layers.18.mamba.conv1d.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.mamba.dt_bias": "model-00007-of-00014.safetensors",
+    "model.layers.18.mamba.in_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.mamba.norm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.mamba.out_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.shared_mlp.input_linear.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.shared_mlp.output_linear.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.block_sparse_moe.input_linear.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.block_sparse_moe.output_linear.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.block_sparse_moe.router.layer.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.mamba.A_log": "model-00007-of-00014.safetensors",
+    "model.layers.19.mamba.D": "model-00007-of-00014.safetensors",
+    "model.layers.19.mamba.conv1d.bias": "model-00007-of-00014.safetensors",
+    "model.layers.19.mamba.conv1d.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.mamba.dt_bias": "model-00007-of-00014.safetensors",
+    "model.layers.19.mamba.in_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.mamba.norm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.mamba.out_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.shared_mlp.input_linear.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.shared_mlp.output_linear.weight": "model-00007-of-00014.safetensors",
+    "model.layers.2.block_sparse_moe.input_linear.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.block_sparse_moe.output_linear.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.block_sparse_moe.router.layer.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.mamba.A_log": "model-00002-of-00014.safetensors",
+    "model.layers.2.mamba.D": "model-00002-of-00014.safetensors",
+    "model.layers.2.mamba.conv1d.bias": "model-00002-of-00014.safetensors",
+    "model.layers.2.mamba.conv1d.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.mamba.dt_bias": "model-00002-of-00014.safetensors",
+    "model.layers.2.mamba.in_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.mamba.norm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.mamba.out_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.shared_mlp.input_linear.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.shared_mlp.output_linear.weight": "model-00002-of-00014.safetensors",
+    "model.layers.20.block_sparse_moe.input_linear.weight": "model-00007-of-00014.safetensors",
+    "model.layers.20.block_sparse_moe.output_linear.weight": "model-00008-of-00014.safetensors",
+    "model.layers.20.block_sparse_moe.router.layer.weight": "model-00008-of-00014.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.20.mamba.A_log": "model-00008-of-00014.safetensors",
+    "model.layers.20.mamba.D": "model-00008-of-00014.safetensors",
+    "model.layers.20.mamba.conv1d.bias": "model-00008-of-00014.safetensors",
+    "model.layers.20.mamba.conv1d.weight": "model-00008-of-00014.safetensors",
+    "model.layers.20.mamba.dt_bias": "model-00008-of-00014.safetensors",
+    "model.layers.20.mamba.in_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.20.mamba.norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.20.mamba.out_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.20.shared_mlp.input_linear.weight": "model-00008-of-00014.safetensors",
+    "model.layers.20.shared_mlp.output_linear.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.block_sparse_moe.input_linear.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.block_sparse_moe.output_linear.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.block_sparse_moe.router.layer.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.mamba.A_log": "model-00008-of-00014.safetensors",
+    "model.layers.21.mamba.D": "model-00008-of-00014.safetensors",
+    "model.layers.21.mamba.conv1d.bias": "model-00008-of-00014.safetensors",
+    "model.layers.21.mamba.conv1d.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.mamba.dt_bias": "model-00008-of-00014.safetensors",
+    "model.layers.21.mamba.in_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.mamba.norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.mamba.out_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.shared_mlp.input_linear.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.shared_mlp.output_linear.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.block_sparse_moe.input_linear.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.block_sparse_moe.output_linear.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.block_sparse_moe.router.layer.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.mamba.A_log": "model-00008-of-00014.safetensors",
+    "model.layers.22.mamba.D": "model-00008-of-00014.safetensors",
+    "model.layers.22.mamba.conv1d.bias": "model-00008-of-00014.safetensors",
+    "model.layers.22.mamba.conv1d.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.mamba.dt_bias": "model-00008-of-00014.safetensors",
+    "model.layers.22.mamba.in_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.mamba.norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.mamba.out_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.shared_mlp.input_linear.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.shared_mlp.output_linear.weight": "model-00008-of-00014.safetensors",
+    "model.layers.23.block_sparse_moe.input_linear.weight": "model-00008-of-00014.safetensors",
+    "model.layers.23.block_sparse_moe.output_linear.weight": "model-00009-of-00014.safetensors",
+    "model.layers.23.block_sparse_moe.router.layer.weight": "model-00009-of-00014.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.23.mamba.A_log": "model-00009-of-00014.safetensors",
+    "model.layers.23.mamba.D": "model-00009-of-00014.safetensors",
+    "model.layers.23.mamba.conv1d.bias": "model-00009-of-00014.safetensors",
+    "model.layers.23.mamba.conv1d.weight": "model-00009-of-00014.safetensors",
+    "model.layers.23.mamba.dt_bias": "model-00009-of-00014.safetensors",
+    "model.layers.23.mamba.in_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.23.mamba.norm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.23.mamba.out_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.23.shared_mlp.input_linear.weight": "model-00009-of-00014.safetensors",
+    "model.layers.23.shared_mlp.output_linear.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.block_sparse_moe.input_linear.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.block_sparse_moe.output_linear.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.block_sparse_moe.router.layer.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.mamba.A_log": "model-00009-of-00014.safetensors",
+    "model.layers.24.mamba.D": "model-00009-of-00014.safetensors",
+    "model.layers.24.mamba.conv1d.bias": "model-00009-of-00014.safetensors",
+    "model.layers.24.mamba.conv1d.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.mamba.dt_bias": "model-00009-of-00014.safetensors",
+    "model.layers.24.mamba.in_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.mamba.norm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.mamba.out_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.shared_mlp.input_linear.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.shared_mlp.output_linear.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.block_sparse_moe.input_linear.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.block_sparse_moe.output_linear.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.block_sparse_moe.router.layer.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.shared_mlp.input_linear.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.shared_mlp.output_linear.weight": "model-00009-of-00014.safetensors",
+    "model.layers.26.block_sparse_moe.input_linear.weight": "model-00009-of-00014.safetensors",
+    "model.layers.26.block_sparse_moe.output_linear.weight": "model-00010-of-00014.safetensors",
+    "model.layers.26.block_sparse_moe.router.layer.weight": "model-00010-of-00014.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.26.mamba.A_log": "model-00010-of-00014.safetensors",
+    "model.layers.26.mamba.D": "model-00010-of-00014.safetensors",
+    "model.layers.26.mamba.conv1d.bias": "model-00010-of-00014.safetensors",
+    "model.layers.26.mamba.conv1d.weight": "model-00010-of-00014.safetensors",
+    "model.layers.26.mamba.dt_bias": "model-00010-of-00014.safetensors",
+    "model.layers.26.mamba.in_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.26.mamba.norm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.26.mamba.out_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.26.shared_mlp.input_linear.weight": "model-00010-of-00014.safetensors",
+    "model.layers.26.shared_mlp.output_linear.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.block_sparse_moe.input_linear.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.block_sparse_moe.output_linear.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.block_sparse_moe.router.layer.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.mamba.A_log": "model-00010-of-00014.safetensors",
+    "model.layers.27.mamba.D": "model-00010-of-00014.safetensors",
+    "model.layers.27.mamba.conv1d.bias": "model-00010-of-00014.safetensors",
+    "model.layers.27.mamba.conv1d.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.mamba.dt_bias": "model-00010-of-00014.safetensors",
+    "model.layers.27.mamba.in_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.mamba.norm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.mamba.out_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.shared_mlp.input_linear.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.shared_mlp.output_linear.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.block_sparse_moe.input_linear.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.block_sparse_moe.output_linear.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.block_sparse_moe.router.layer.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.mamba.A_log": "model-00010-of-00014.safetensors",
+    "model.layers.28.mamba.D": "model-00010-of-00014.safetensors",
+    "model.layers.28.mamba.conv1d.bias": "model-00010-of-00014.safetensors",
+    "model.layers.28.mamba.conv1d.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.mamba.dt_bias": "model-00010-of-00014.safetensors",
+    "model.layers.28.mamba.in_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.mamba.norm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.mamba.out_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.shared_mlp.input_linear.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.shared_mlp.output_linear.weight": "model-00010-of-00014.safetensors",
+    "model.layers.29.block_sparse_moe.input_linear.weight": "model-00010-of-00014.safetensors",
+    "model.layers.29.block_sparse_moe.output_linear.weight": "model-00011-of-00014.safetensors",
+    "model.layers.29.block_sparse_moe.router.layer.weight": "model-00011-of-00014.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.29.mamba.A_log": "model-00011-of-00014.safetensors",
+    "model.layers.29.mamba.D": "model-00011-of-00014.safetensors",
+    "model.layers.29.mamba.conv1d.bias": "model-00011-of-00014.safetensors",
+    "model.layers.29.mamba.conv1d.weight": "model-00011-of-00014.safetensors",
+    "model.layers.29.mamba.dt_bias": "model-00011-of-00014.safetensors",
+    "model.layers.29.mamba.in_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.29.mamba.norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.29.mamba.out_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.29.shared_mlp.input_linear.weight": "model-00011-of-00014.safetensors",
+    "model.layers.29.shared_mlp.output_linear.weight": "model-00011-of-00014.safetensors",
+    "model.layers.3.block_sparse_moe.input_linear.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.block_sparse_moe.output_linear.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.block_sparse_moe.router.layer.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mamba.A_log": "model-00002-of-00014.safetensors",
+    "model.layers.3.mamba.D": "model-00002-of-00014.safetensors",
+    "model.layers.3.mamba.conv1d.bias": "model-00002-of-00014.safetensors",
+    "model.layers.3.mamba.conv1d.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mamba.dt_bias": "model-00002-of-00014.safetensors",
+    "model.layers.3.mamba.in_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mamba.norm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mamba.out_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.shared_mlp.input_linear.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.shared_mlp.output_linear.weight": "model-00002-of-00014.safetensors",
+    "model.layers.30.block_sparse_moe.input_linear.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.block_sparse_moe.output_linear.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.block_sparse_moe.router.layer.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.mamba.A_log": "model-00011-of-00014.safetensors",
+    "model.layers.30.mamba.D": "model-00011-of-00014.safetensors",
+    "model.layers.30.mamba.conv1d.bias": "model-00011-of-00014.safetensors",
+    "model.layers.30.mamba.conv1d.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.mamba.dt_bias": "model-00011-of-00014.safetensors",
+    "model.layers.30.mamba.in_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.mamba.norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.mamba.out_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.shared_mlp.input_linear.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.shared_mlp.output_linear.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.block_sparse_moe.input_linear.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.block_sparse_moe.output_linear.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.block_sparse_moe.router.layer.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.mamba.A_log": "model-00011-of-00014.safetensors",
+    "model.layers.31.mamba.D": "model-00011-of-00014.safetensors",
+    "model.layers.31.mamba.conv1d.bias": "model-00011-of-00014.safetensors",
+    "model.layers.31.mamba.conv1d.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.mamba.dt_bias": "model-00011-of-00014.safetensors",
+    "model.layers.31.mamba.in_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.mamba.norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.mamba.out_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.shared_mlp.input_linear.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.shared_mlp.output_linear.weight": "model-00011-of-00014.safetensors",
+    "model.layers.32.block_sparse_moe.input_linear.weight": "model-00011-of-00014.safetensors",
+    "model.layers.32.block_sparse_moe.output_linear.weight": "model-00012-of-00014.safetensors",
+    "model.layers.32.block_sparse_moe.router.layer.weight": "model-00012-of-00014.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.32.mamba.A_log": "model-00012-of-00014.safetensors",
+    "model.layers.32.mamba.D": "model-00012-of-00014.safetensors",
+    "model.layers.32.mamba.conv1d.bias": "model-00012-of-00014.safetensors",
+    "model.layers.32.mamba.conv1d.weight": "model-00012-of-00014.safetensors",
+    "model.layers.32.mamba.dt_bias": "model-00012-of-00014.safetensors",
+    "model.layers.32.mamba.in_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.32.mamba.norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.32.mamba.out_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.32.shared_mlp.input_linear.weight": "model-00012-of-00014.safetensors",
+    "model.layers.32.shared_mlp.output_linear.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.block_sparse_moe.input_linear.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.block_sparse_moe.output_linear.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.block_sparse_moe.router.layer.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.mamba.A_log": "model-00012-of-00014.safetensors",
+    "model.layers.33.mamba.D": "model-00012-of-00014.safetensors",
+    "model.layers.33.mamba.conv1d.bias": "model-00012-of-00014.safetensors",
+    "model.layers.33.mamba.conv1d.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.mamba.dt_bias": "model-00012-of-00014.safetensors",
+    "model.layers.33.mamba.in_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.mamba.norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.mamba.out_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.shared_mlp.input_linear.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.shared_mlp.output_linear.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.block_sparse_moe.input_linear.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.block_sparse_moe.output_linear.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.block_sparse_moe.router.layer.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.mamba.A_log": "model-00012-of-00014.safetensors",
+    "model.layers.34.mamba.D": "model-00012-of-00014.safetensors",
+    "model.layers.34.mamba.conv1d.bias": "model-00012-of-00014.safetensors",
+    "model.layers.34.mamba.conv1d.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.mamba.dt_bias": "model-00012-of-00014.safetensors",
+    "model.layers.34.mamba.in_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.mamba.norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.mamba.out_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.shared_mlp.input_linear.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.shared_mlp.output_linear.weight": "model-00012-of-00014.safetensors",
+    "model.layers.35.block_sparse_moe.input_linear.weight": "model-00012-of-00014.safetensors",
+    "model.layers.35.block_sparse_moe.output_linear.weight": "model-00013-of-00014.safetensors",
+    "model.layers.35.block_sparse_moe.router.layer.weight": "model-00013-of-00014.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.35.shared_mlp.input_linear.weight": "model-00013-of-00014.safetensors",
+    "model.layers.35.shared_mlp.output_linear.weight": "model-00013-of-00014.safetensors",
+    "model.layers.36.block_sparse_moe.input_linear.weight": "model-00013-of-00014.safetensors",
+    "model.layers.36.block_sparse_moe.output_linear.weight": "model-00013-of-00014.safetensors",
+    "model.layers.36.block_sparse_moe.router.layer.weight": "model-00013-of-00014.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.36.mamba.A_log": "model-00013-of-00014.safetensors",
+    "model.layers.36.mamba.D": "model-00013-of-00014.safetensors",
+    "model.layers.36.mamba.conv1d.bias": "model-00013-of-00014.safetensors",
+    "model.layers.36.mamba.conv1d.weight": "model-00013-of-00014.safetensors",
+    "model.layers.36.mamba.dt_bias": "model-00013-of-00014.safetensors",
+    "model.layers.36.mamba.in_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.36.mamba.norm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.36.mamba.out_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.36.shared_mlp.input_linear.weight": "model-00013-of-00014.safetensors",
+    "model.layers.36.shared_mlp.output_linear.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.block_sparse_moe.input_linear.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.block_sparse_moe.output_linear.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.block_sparse_moe.router.layer.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.mamba.A_log": "model-00013-of-00014.safetensors",
+    "model.layers.37.mamba.D": "model-00013-of-00014.safetensors",
+    "model.layers.37.mamba.conv1d.bias": "model-00013-of-00014.safetensors",
+    "model.layers.37.mamba.conv1d.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.mamba.dt_bias": "model-00013-of-00014.safetensors",
+    "model.layers.37.mamba.in_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.mamba.norm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.mamba.out_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.shared_mlp.input_linear.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.shared_mlp.output_linear.weight": "model-00013-of-00014.safetensors",
+    "model.layers.38.block_sparse_moe.input_linear.weight": "model-00013-of-00014.safetensors",
+    "model.layers.38.block_sparse_moe.output_linear.weight": "model-00014-of-00014.safetensors",
+    "model.layers.38.block_sparse_moe.router.layer.weight": "model-00014-of-00014.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.38.mamba.A_log": "model-00014-of-00014.safetensors",
+    "model.layers.38.mamba.D": "model-00014-of-00014.safetensors",
+    "model.layers.38.mamba.conv1d.bias": "model-00014-of-00014.safetensors",
+    "model.layers.38.mamba.conv1d.weight": "model-00014-of-00014.safetensors",
+    "model.layers.38.mamba.dt_bias": "model-00014-of-00014.safetensors",
+    "model.layers.38.mamba.in_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.38.mamba.norm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.38.mamba.out_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.38.shared_mlp.input_linear.weight": "model-00014-of-00014.safetensors",
+    "model.layers.38.shared_mlp.output_linear.weight": "model-00014-of-00014.safetensors",
+    "model.layers.39.block_sparse_moe.input_linear.weight": "model-00014-of-00014.safetensors",
+    "model.layers.39.block_sparse_moe.output_linear.weight": "model-00014-of-00014.safetensors",
+    "model.layers.39.block_sparse_moe.router.layer.weight": "model-00014-of-00014.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.39.mamba.A_log": "model-00014-of-00014.safetensors",
+    "model.layers.39.mamba.D": "model-00014-of-00014.safetensors",
+    "model.layers.39.mamba.conv1d.bias": "model-00014-of-00014.safetensors",
+    "model.layers.39.mamba.conv1d.weight": "model-00014-of-00014.safetensors",
+    "model.layers.39.mamba.dt_bias": "model-00014-of-00014.safetensors",
+    "model.layers.39.mamba.in_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.39.mamba.norm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.39.mamba.out_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.39.shared_mlp.input_linear.weight": "model-00014-of-00014.safetensors",
+    "model.layers.39.shared_mlp.output_linear.weight": "model-00014-of-00014.safetensors",
+    "model.layers.4.block_sparse_moe.input_linear.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.block_sparse_moe.output_linear.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.block_sparse_moe.router.layer.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mamba.A_log": "model-00002-of-00014.safetensors",
+    "model.layers.4.mamba.D": "model-00002-of-00014.safetensors",
+    "model.layers.4.mamba.conv1d.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.mamba.conv1d.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mamba.dt_bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.mamba.in_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mamba.norm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mamba.out_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.shared_mlp.input_linear.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.shared_mlp.output_linear.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.block_sparse_moe.input_linear.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.block_sparse_moe.output_linear.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.block_sparse_moe.router.layer.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.shared_mlp.input_linear.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.shared_mlp.output_linear.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.block_sparse_moe.input_linear.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.block_sparse_moe.output_linear.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.block_sparse_moe.router.layer.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.mamba.A_log": "model-00003-of-00014.safetensors",
+    "model.layers.6.mamba.D": "model-00003-of-00014.safetensors",
+    "model.layers.6.mamba.conv1d.bias": "model-00003-of-00014.safetensors",
+    "model.layers.6.mamba.conv1d.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.mamba.dt_bias": "model-00003-of-00014.safetensors",
+    "model.layers.6.mamba.in_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.mamba.norm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.mamba.out_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.shared_mlp.input_linear.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.shared_mlp.output_linear.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.block_sparse_moe.input_linear.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.block_sparse_moe.output_linear.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.block_sparse_moe.router.layer.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.mamba.A_log": "model-00003-of-00014.safetensors",
+    "model.layers.7.mamba.D": "model-00003-of-00014.safetensors",
+    "model.layers.7.mamba.conv1d.bias": "model-00003-of-00014.safetensors",
+    "model.layers.7.mamba.conv1d.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.mamba.dt_bias": "model-00003-of-00014.safetensors",
+    "model.layers.7.mamba.in_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.mamba.norm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.mamba.out_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.shared_mlp.input_linear.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.shared_mlp.output_linear.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.block_sparse_moe.input_linear.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.block_sparse_moe.output_linear.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.block_sparse_moe.router.layer.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.mamba.A_log": "model-00004-of-00014.safetensors",
+    "model.layers.8.mamba.D": "model-00004-of-00014.safetensors",
+    "model.layers.8.mamba.conv1d.bias": "model-00004-of-00014.safetensors",
+    "model.layers.8.mamba.conv1d.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.mamba.dt_bias": "model-00004-of-00014.safetensors",
+    "model.layers.8.mamba.in_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.mamba.norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.mamba.out_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.shared_mlp.input_linear.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.shared_mlp.output_linear.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.block_sparse_moe.input_linear.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.block_sparse_moe.output_linear.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.block_sparse_moe.router.layer.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.mamba.A_log": "model-00004-of-00014.safetensors",
+    "model.layers.9.mamba.D": "model-00004-of-00014.safetensors",
+    "model.layers.9.mamba.conv1d.bias": "model-00004-of-00014.safetensors",
+    "model.layers.9.mamba.conv1d.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.mamba.dt_bias": "model-00004-of-00014.safetensors",
+    "model.layers.9.mamba.in_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.mamba.norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.mamba.out_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.shared_mlp.input_linear.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.shared_mlp.output_linear.weight": "model-00004-of-00014.safetensors",
+    "model.norm.weight": "model-00014-of-00014.safetensors"
+  }
+}

model.sig

@@ -0,0 +1 @@
+{"mediaType": "application/vnd.dev.sigstore.bundle.v0.3+json", "verificationMaterial": {"certificate": {"rawBytes": "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"}, "tlogEntries": [{"logIndex": "545484426", "logId": {"keyId": "wNI9atQGlz+VWfO6LRygH4QUfY/8W4RFwiT5i5WRgB0="}, "kindVersion": {"kind": "dsse", "version": "0.0.1"}, "integratedTime": "1758540514", "inclusionPromise": {"signedEntryTimestamp": "MEUCIB4NlgODhPCqB+oW1lqB9RGze5KYbIZk19kGKOSC9BsnAiEApWwE3N2SmuFdpn+hJoerAwhfl92GN3ZSFUePjUFrONY="}, "inclusionProof": {"logIndex": "423580164", "rootHash": "W3ecKohuYLmQqUbzWFpGwu53rx9lIOQw11/kJo7cqzU=", "treeSize": "423580165", "hashes": ["VhFHFyq9/zlPFAUMEP2f3ZkHeF5izVHRtIvOGmNHmXU=", "m5k1vhUsrUbhznRpNmNss6vpQ/KDybn1NcBmjMEtOfA=", "77X2OfSUSMAEq2fndRFUTzBUL1JPUULd6JBgblhr8mI=", "n6NUmUEwWQYvugSlwJsZe5wOn1gw3JmjS0ZQaGSltYg=", "1vS/00hbOTJ3heYZq20BDIPx4nPbf/Por7tpCT8UXW4=", "9u9OTSyj4asXRH3Y745tvCNR9pdVqkDsRMLMfb3mBSo=", "cyVL5e3kVYJcNDYZJOR+4P2qHQfN06gdNpNZmbdub3w=", "dmLfZXwB/j/R//im2zDb0MIkl0JRXsiZ3elHeagb7SI=", "SSVfltYSWmchaPYZxhSF4nU5lLNCbc8IL5vyvDeyMUo=", "pgVI1ynvGL4PQQaoRZ9e2Gfo4FJnZnCnLbkLmrsyvpY=", "rO8wDSOjmY8VkspFqYaJS4TV5HxywICMlHM8gTxXkAA=", "1mfy94KpcItqshH9+gwqV6jccupcaMpVsF28New8zDY=", "vS7O4ozHIQZJWBiov+mkpI27GE8zAmVCEkRcP3NDyNE="], "checkpoint": {"envelope": "rekor.sigstore.dev - 1193050959916656506\n423580165\nW3ecKohuYLmQqUbzWFpGwu53rx9lIOQw11/kJo7cqzU=\n\n\u2014 rekor.sigstore.dev wNI9ajBEAiAOZsZfuRm79zV0YDc5fN+LSY/uBdK0OHzCeE3QPCIoFgIgDupaq9i/ElUMfacIHmgv1eRTLFTjjPUpD0CZ8tG3u2E=\n"}}, "canonicalizedBody": "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"}], "timestampVerificationData": {}}, "dsseEnvelope": {"payload": "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", "payloadType": "application/vnd.in-toto+json", "signatures": [{"sig": "MEYCIQCC17hPDaZkNMabsxMceSVQc/42uVtCvcrBy1ZibTKqxAIhAKFbFRA4lkDZetWdhVIHPsLtIhZ+YaTiX7vOWEnHWVC7"}]}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|unk|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,783 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100256": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100257": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100261": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100262": {
+      "content": "<|filename|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100263": {
+      "content": "<|reponame|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100264": {
+      "content": "<|start_of_role|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|end_of_role|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<|unused_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100267": {
+      "content": "<|start_of_plugin|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100268": {
+      "content": "<|end_of_plugin|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100269": {
+      "content": "<|unk|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100270": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100271": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100272": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100273": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100274": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100275": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100276": {
+      "content": "<think_on>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100277": {
+      "content": "<think_off>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100278": {
+      "content": "<schema>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100279": {
+      "content": "</schema>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100280": {
+      "content": "<tools>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100281": {
+      "content": "</tools>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100282": {
+      "content": "<documents>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100283": {
+      "content": "</documents>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100284": {
+      "content": "<|unused_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100285": {
+      "content": "<|unused_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100286": {
+      "content": "<|unused_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100287": {
+      "content": "<|unused_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100288": {
+      "content": "<|unused_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100289": {
+      "content": "<|unused_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100290": {
+      "content": "<|unused_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100291": {
+      "content": "<|unused_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100292": {
+      "content": "<|unused_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100293": {
+      "content": "<|unused_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100294": {
+      "content": "<|unused_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100295": {
+      "content": "<|unused_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100296": {
+      "content": "<|unused_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100297": {
+      "content": "<|unused_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100298": {
+      "content": "<|unused_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100299": {
+      "content": "<|unused_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100300": {
+      "content": "<|unused_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100301": {
+      "content": "<|unused_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100302": {
+      "content": "<|unused_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100303": {
+      "content": "<|unused_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100304": {
+      "content": "<|unused_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100305": {
+      "content": "<|unused_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100306": {
+      "content": "<|unused_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100307": {
+      "content": "<|unused_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100308": {
+      "content": "<|unused_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100309": {
+      "content": "<|unused_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100310": {
+      "content": "<|unused_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100311": {
+      "content": "<|unused_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100312": {
+      "content": "<|unused_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100313": {
+      "content": "<|unused_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100314": {
+      "content": "<|unused_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100315": {
+      "content": "<|unused_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100316": {
+      "content": "<|unused_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100317": {
+      "content": "<|unused_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100318": {
+      "content": "<|unused_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100319": {
+      "content": "<|unused_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100320": {
+      "content": "<|unused_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100321": {
+      "content": "<|unused_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100322": {
+      "content": "<|unused_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100323": {
+      "content": "<|unused_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100324": {
+      "content": "<|unused_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100325": {
+      "content": "<|unused_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100326": {
+      "content": "<|unused_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100327": {
+      "content": "<|unused_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100328": {
+      "content": "<|unused_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100329": {
+      "content": "<|unused_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100330": {
+      "content": "<|unused_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100331": {
+      "content": "<|unused_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100332": {
+      "content": "<|unused_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100333": {
+      "content": "<|unused_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100334": {
+      "content": "<|unused_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100335": {
+      "content": "<|unused_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100336": {
+      "content": "<|unused_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100337": {
+      "content": "<|unused_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100338": {
+      "content": "<|unused_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100339": {
+      "content": "<|unused_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100340": {
+      "content": "<|unused_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100341": {
+      "content": "<|unused_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100342": {
+      "content": "<|unused_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100343": {
+      "content": "<|unused_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100344": {
+      "content": "<|unused_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100345": {
+      "content": "<|unused_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100346": {
+      "content": "<|unused_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100347": {
+      "content": "<|unused_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100348": {
+      "content": "<|unused_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100349": {
+      "content": "<|unused_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100350": {
+      "content": "<|unused_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100351": {
+      "content": "<|unused_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|end_of_text|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|end_of_text|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|unk|>"
+}