Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ 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.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,32 @@
+{
+  "</function>": 151672,
+  "</parameter>": 151671,
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<function=": 151669,
+  "<parameter=": 151670,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,160 @@
+{% macro render_item_list(item_list, tag_name='required') %}
+    {%- if item_list is defined and item_list is iterable and item_list | length > 0 %}
+        {%- if tag_name %}{{- '\n<' ~ tag_name ~ '>' -}}{% endif %}
+            {{- '[' }}
+                {%- for item in item_list -%}
+                    {%- if loop.index > 1 %}{{- ", "}}{% endif -%}
+                    {%- if item is string -%}
+                        {{ "`" ~ item ~ "`" }}
+                    {%- else -%}
+                        {{ item }}
+                    {%- endif -%}
+                {%- endfor -%}
+            {{- ']' }}
+        {%- if tag_name %}{{- '</' ~ tag_name ~ '>' -}}{% endif %}
+    {%- endif %}
+{% endmacro %}
+
+{%- if not add_generation_prompt is defined %}
+    {% set add_generation_prompt = false %}
+{%- endif %}
+
+{%- set ns = namespace(is_first=false, system_prompt='You are Nex, a helpful assistant developed by Shanghai Innovation Institution and its entrepreneurial partners.', is_first_sp=true, is_last_user=false) %}
+{%- for message in messages %}
+    {%- if message['role'] == 'system' %}
+        {%- if ns.is_first_sp %}
+            {% set ns.system_prompt = message['content'] %}
+            {% set ns.is_first_sp = false %}
+        {%- else %}
+            {% set ns.system_prompt = ns.system_prompt ~ '\n\n' ~ message['content'] %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor -%}
+
+{%- if tools is defined and tools is not none %}
+    {% set tool_ns = namespace(text='You are a helpful assistant with tool calling capabilities. '
+        'When a tool call is needed, you MUST use the following format to issue the call:\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:\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\n'
+        'You have access to the following functions:\n\n'
+        '<tools>') %}
+    {% for tool in tools %}
+        {%- if tool.function is defined %}
+            {%- set tool = tool.function %}
+        {%- endif %}
+        {% set tool_ns.text = tool_ns.text ~ '\n<function>\n<name>' ~ tool.name ~ '</name>' %}
+        {% set tool_ns.text = tool_ns.text ~ '\n<description>' ~ (tool.description | trim) ~ '</description>' %}
+        {% set tool_ns.text = tool_ns.text ~ '\n<parameters>' %}
+        {%- for param_name, param_fields in tool.parameters.properties|items %}
+            {% set tool_ns.text = tool_ns.text ~ '\n<parameter>' %}
+            {% set tool_ns.text = tool_ns.text ~ '\n<name>' ~ param_name ~ '</name>' %}
+            {%- if param_fields.type is defined %}
+                {% set tool_ns.text = tool_ns.text ~ '\n<type>' ~ (param_fields.type | string) ~ '</type>' %}
+            {%- endif %}
+            {%- if param_fields.description is defined %}
+                {% set tool_ns.text = tool_ns.text ~ '\n<description>' ~ (param_fields.description | trim) ~ '</description>' %}
+            {%- endif %}
+            {%- if param_fields.enum is defined and param_fields.enum is iterable and param_fields.enum | length > 0 %}
+                {% set tool_ns.text = tool_ns.text ~ render_item_list(param_fields.enum, 'enum') %}
+            {%- endif %}
+            {%- set handled_keys = ['type', 'description', 'enum', 'required'] %}
+            {%- for json_key in param_fields.keys() | reject("in", handled_keys) %}
+                {%- set normed_json_key = json_key | replace("-", "_") | replace(" ", "_") | replace("$", "") %}
+                {%- if param_fields[json_key] is mapping %}
+                    {% set tool_ns.text = tool_ns.text ~ '\n<' ~ normed_json_key ~ '>' ~ (param_fields[json_key] | tojson | safe) ~ '</' ~ normed_json_key ~ '>' %}
+                {%- else %}
+                    {% set tool_ns.text = tool_ns.text ~ '\n<' ~ normed_json_key ~ '>' ~ (param_fields[json_key] | string) ~ '</' ~ normed_json_key ~ '>' %}
+                {%- endif %}
+            {%- endfor %}
+            {%- if param_fields.required is defined and param_fields.required is iterable and param_fields.required | length > 0 %}
+                {% set tool_ns.text = tool_ns.text ~ render_item_list(param_fields.required, 'required') %}
+            {%- endif %}
+            {% set tool_ns.text = tool_ns.text ~ '\n</parameter>' %}
+        {%- endfor %}
+        {%- if tool.parameters.required is defined and tool.parameters.required is iterable and tool.parameters.required | length > 0 %}
+            {% set tool_ns.text = tool_ns.text ~ render_item_list(tool.parameters.required, 'required') %}
+        {%- endif %}
+        {% set tool_ns.text = tool_ns.text ~ '\n</parameters>' %}
+        {%- if tool.return is defined %}
+            {%- if tool.return is mapping %}
+                {% set tool_ns.text = tool_ns.text ~ '\n<return>' ~ (tool.return | tojson | safe) ~ '</return>' %}
+            {%- else %}
+                {% set tool_ns.text = tool_ns.text ~ '\n<return>' ~ (tool.return | string) ~ '</return>' %}
+            {%- endif %}
+        {%- endif %}
+        {% set tool_ns.text = tool_ns.text ~ '\n</function>' %}
+    {% endfor %}
+    {% set tool_ns.text = tool_ns.text ~ '\n</tools>' %}
+    {% set ns.system_prompt = ns.system_prompt ~ '\n\n' ~ tool_ns.text %}
+{%- endif %}
+
+{%- if ns.system_prompt %}
+    {{- '<|im_start|>system\n' ~ ns.system_prompt ~ '<|im_end|>\n' }}
+{%- endif %}
+
+{%- for message in messages %}
+    {% set content = message['content'] %}
+    {%- if content is none %}
+        {% set content = '' %}
+    {%- endif %}
+    {%- if message['role'] == 'user' %}
+        {%- set ns.is_first = false -%}
+        {%- set ns.is_last_user = true -%}
+        {{- '<|im_start|>user\n' ~ content ~ '<|im_end|>\n' }}
+    {%- endif %}
+    {%- if message['role'] == 'assistant' %}
+        {% if '</think>' in content %}
+            {% set content = content.split('</think>')[-1] %}
+        {% endif %}
+    {% endif %}
+    {%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}
+        {%- set ns.is_last_user = false -%}
+        {%- set ns.is_first = false %}
+        {{- '<|im_start|>assistant' }}
+        {%- if content is defined and content is not none and content | trim | length > 0 %}
+            {{- '\n' + content | trim + '\n' }}
+        {%- endif %}
+        {%- for tool in message['tool_calls'] %}
+            {%- if tool.function is defined %}
+                {%- set tool_call = tool.function %}
+            {%- else %}
+                {%- set tool_call = tool %}
+            {%- endif %}
+            {{- '\n<tool_call>\n<function=' ~ tool_call.name ~ '>\n' }}
+            {%- 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 if args_value is string else args_value | string %}
+                    {{- args_value }}
+                    {{- '\n</parameter>\n' }}
+                {%- endfor %}
+            {%- endif %}
+            {{- '</function>\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n'}}
+    {%- endif %}
+    {%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none)%}
+        {%- set ns.is_last_user = false -%}
+        {{- '<|im_start|>assistant\n' ~ content ~ '<|im_end|>\n'}}
+    {%- endif %}
+    {%- if message['role'] == 'tool' %}
+        {%- set ns.is_last_user = false -%}
+        {%- if loop.previtem and loop.previtem['role'] != 'tool' %}
+            {{- '<|im_start|>user\n' }}
+        {%- endif %}
+        {{- '<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>\n' }}
+        {%- if not loop.last and loop.nextitem['role'] != 'tool' %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor -%}
+{% if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n'}}
+{%- endif %}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 25600,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 64,
+  "model_type": "qwen3",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7b8317b6e65a1e2e831d01394d93e03edf3f689c694d54c4ffc3701373127a5
+size 4275623344

model-00002-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f9cb68f4fb4cfcd4ec8397940ef6ced5d4cfa76096580aeddcad84d7ce5aab5
+size 4162935856

model-00003-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd2ad2be846899692a5e7e9bf4ef35fe5dac1bb6307ba016ad380f822d0d455d
+size 4162935856

model-00004-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93210b1e2df7a33008d03ed120264e2c72473e7ac7d385a30aa52cd0479515e7
+size 4267815280

model-00005-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1a9936e8c6282917931487128320c3954fb69e3a1b254de452fd22fd4b449c6
+size 4246822096

model-00006-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e104dfa89c1fb8193f21d938c57dc9f805df03f4ae97f29d6ce7d6f1697533de
+size 4162935896

model-00007-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e79c4c22016985d1cd555e30fc0f03f3d97068e883b4e45e725a92621b6ef36
+size 4267815304

model-00008-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb9c8c2375a06e748eb63ec19208420bab8f00c796f4a595a0a821497b179115
+size 4246822096

model-00009-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d7739f9f74a4da18a058fcded24ca254725b751b7b603b920456e934b60678e
+size 4162935896

model-00010-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:490c076b246c52c2c3932543cee7a24d8a51f1f4b70e086e98b81eb43b52d6db
+size 4267815304

model-00011-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c0043732eaff8ee37f163ffa28595840ca0080b714d28831886d9e6e831421a
+size 4246822096

model-00012-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:318287086dedc8eed95622f9c15460e2efdf986cb2c785307069b96b893cf4e0
+size 4162935896

model-00013-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc6d2e60449284764e5ac5f52e45e775f906a780a9615709b2720604c0ddb196
+size 4267815304

model-00014-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c901e8261e02cdb909f84447aa3359c0f7d6d7337ed62835e7375df63f6a5197
+size 4246822096

model-00015-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d6c82abacc80c020375d6eb733ec38d22a4ca48049607d861b40aa12c553e98
+size 4162935896

model-00016-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07ead3e8ecd2608f6aa98bcfc82e45f43651e68451a2bd9f18de6522254adb25
+size 2212540008

model.safetensors.index.json

@@ -0,0 +1,712 @@
+{
+  "metadata": {},
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00001.safetensors",
+    "model.norm.weight": "model-00001-of-00001.safetensors",
+    "lm_head.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00001.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00001.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00001.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00001.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00001.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00002-of-00001.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00002-of-00001.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00001.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00001.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00001.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00001.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00001.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00001.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00001.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00001.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00001.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00002-of-00001.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00002-of-00001.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00001.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00001.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00001.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00001.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00001.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00001.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00001.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00001.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00001.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00001.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00001.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00001.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00001.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00001.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00001.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00001.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00001.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00001.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00001.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00001.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00001.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00002-of-00001.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00001.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00001.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00001.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00001.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00001.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00001.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00001.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00001.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00001.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00003-of-00001.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00003-of-00001.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00001.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00001.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00001.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00001.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00001.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00001.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00001.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00001.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00001.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00003-of-00001.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00003-of-00001.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00001.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00001.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00001.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00001.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00001.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00001.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00001.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00001.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00001.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00003-of-00001.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00003-of-00001.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00001.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00001.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00001.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00001.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00001.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00001.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00001.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00001.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00001.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00003-of-00001.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00003-of-00001.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00001.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00001.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00001.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00001.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00001.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00001.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00001.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00001.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00004-of-00001.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00004-of-00001.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00001.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00001.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00004-of-00001.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00004-of-00001.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00001.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00001.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00004-of-00001.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00004-of-00001.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00001.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00001.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00004-of-00001.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00004-of-00001.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00001.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00001.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00004-of-00001.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00004-of-00001.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00001.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00001.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00001.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00005-of-00001.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00005-of-00001.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00005-of-00001.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00001.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00005-of-00001.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00005-of-00001.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00001.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00001.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00001.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00001.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00001.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00005-of-00001.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00005-of-00001.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00001.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00001.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00005-of-00001.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00005-of-00001.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00001.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00001.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00001.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00001.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00001.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00001.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00001.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00001.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00001.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00005-of-00001.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00005-of-00001.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00001.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00001.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00001.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00001.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00001.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00001.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00001.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00001.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00001.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00005-of-00001.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00005-of-00001.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00001.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00001.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00001.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00001.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00001.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00006-of-00001.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00006-of-00001.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00006-of-00001.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00001.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00006-of-00001.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00006-of-00001.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00001.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00001.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00001.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00001.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00001.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00006-of-00001.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00006-of-00001.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00006-of-00001.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00001.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00006-of-00001.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00006-of-00001.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00001.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00001.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00001.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00001.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00001.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00001.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00001.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00006-of-00001.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00001.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00006-of-00001.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00006-of-00001.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00001.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00001.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00001.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00001.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00001.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00001.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00001.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00001.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00001.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00006-of-00001.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00006-of-00001.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00001.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00001.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00001.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00001.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00001.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00001.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00007-of-00001.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00001.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00007-of-00001.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00007-of-00001.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00007-of-00001.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00001.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00007-of-00001.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00007-of-00001.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00007-of-00001.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00001.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00007-of-00001.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00007-of-00001.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00007-of-00001.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00001.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00007-of-00001.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00007-of-00001.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00007-of-00001.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00001.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00007-of-00001.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00007-of-00001.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00001.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00001.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00001.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00008-of-00001.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00008-of-00001.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00008-of-00001.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00001.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00008-of-00001.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00008-of-00001.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00001.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00001.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00001.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00001.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00001.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00008-of-00001.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00008-of-00001.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00008-of-00001.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00001.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00008-of-00001.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00008-of-00001.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00001.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00001.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00001.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00001.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00001.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00008-of-00001.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00008-of-00001.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00008-of-00001.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00001.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00008-of-00001.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00008-of-00001.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00001.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00001.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00001.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00001.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00001.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00008-of-00001.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00008-of-00001.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00008-of-00001.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00001.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00008-of-00001.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00008-of-00001.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00001.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00001.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00001.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00001.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00001.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00009-of-00001.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00009-of-00001.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00009-of-00001.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00009-of-00001.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00009-of-00001.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00009-of-00001.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00009-of-00001.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00009-of-00001.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00009-of-00001.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00009-of-00001.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00009-of-00001.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00009-of-00001.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00009-of-00001.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00009-of-00001.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00001.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00009-of-00001.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00009-of-00001.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00009-of-00001.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00009-of-00001.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00009-of-00001.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00009-of-00001.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00009-of-00001.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00009-of-00001.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00009-of-00001.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00009-of-00001.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00001.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00009-of-00001.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00009-of-00001.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00001.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00001.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00001.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00001.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00009-of-00001.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00009-of-00001.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00009-of-00001.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00009-of-00001.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00001.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00009-of-00001.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00009-of-00001.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00001.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00001.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00001.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00001.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00001.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00009-of-00001.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00010-of-00001.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00010-of-00001.safetensors",
+    "model.layers.36.self_attn.k_norm.weight": "model-00010-of-00001.safetensors",
+    "model.layers.36.self_attn.q_norm.weight": "model-00010-of-00001.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00010-of-00001.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00010-of-00001.safetensors",
+    "model.layers.37.self_attn.k_norm.weight": "model-00010-of-00001.safetensors",
+    "model.layers.37.self_attn.q_norm.weight": "model-00010-of-00001.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00010-of-00001.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00010-of-00001.safetensors",
+    "model.layers.38.self_attn.k_norm.weight": "model-00010-of-00001.safetensors",
+    "model.layers.38.self_attn.q_norm.weight": "model-00010-of-00001.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00010-of-00001.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00010-of-00001.safetensors",
+    "model.layers.39.self_attn.k_norm.weight": "model-00010-of-00001.safetensors",
+    "model.layers.39.self_attn.q_norm.weight": "model-00010-of-00001.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00010-of-00001.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00010-of-00001.safetensors",
+    "model.layers.40.self_attn.k_norm.weight": "model-00010-of-00001.safetensors",
+    "model.layers.40.self_attn.q_norm.weight": "model-00010-of-00001.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00010-of-00001.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00011-of-00001.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00011-of-00001.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00011-of-00001.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00011-of-00001.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00011-of-00001.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00011-of-00001.safetensors",
+    "model.layers.41.self_attn.k_norm.weight": "model-00011-of-00001.safetensors",
+    "model.layers.41.self_attn.q_norm.weight": "model-00011-of-00001.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00011-of-00001.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00011-of-00001.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00011-of-00001.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00011-of-00001.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00011-of-00001.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00011-of-00001.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00011-of-00001.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00011-of-00001.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00011-of-00001.safetensors",
+    "model.layers.42.self_attn.k_norm.weight": "model-00011-of-00001.safetensors",
+    "model.layers.42.self_attn.q_norm.weight": "model-00011-of-00001.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00011-of-00001.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00011-of-00001.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00011-of-00001.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00011-of-00001.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00011-of-00001.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00011-of-00001.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00011-of-00001.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00011-of-00001.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00011-of-00001.safetensors",
+    "model.layers.43.self_attn.k_norm.weight": "model-00011-of-00001.safetensors",
+    "model.layers.43.self_attn.q_norm.weight": "model-00011-of-00001.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00011-of-00001.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00011-of-00001.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00011-of-00001.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00011-of-00001.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00011-of-00001.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00011-of-00001.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00011-of-00001.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00011-of-00001.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00011-of-00001.safetensors",
+    "model.layers.44.self_attn.k_norm.weight": "model-00011-of-00001.safetensors",
+    "model.layers.44.self_attn.q_norm.weight": "model-00011-of-00001.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00011-of-00001.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00011-of-00001.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00011-of-00001.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00011-of-00001.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00011-of-00001.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00012-of-00001.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00012-of-00001.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00012-of-00001.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00012-of-00001.safetensors",
+    "model.layers.45.self_attn.k_norm.weight": "model-00012-of-00001.safetensors",
+    "model.layers.45.self_attn.q_norm.weight": "model-00012-of-00001.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00012-of-00001.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00012-of-00001.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00012-of-00001.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00012-of-00001.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00012-of-00001.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00012-of-00001.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00012-of-00001.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00012-of-00001.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00012-of-00001.safetensors",
+    "model.layers.46.self_attn.k_norm.weight": "model-00012-of-00001.safetensors",
+    "model.layers.46.self_attn.q_norm.weight": "model-00012-of-00001.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00012-of-00001.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00012-of-00001.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00012-of-00001.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00012-of-00001.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00012-of-00001.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00012-of-00001.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00012-of-00001.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00012-of-00001.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00012-of-00001.safetensors",
+    "model.layers.47.self_attn.k_norm.weight": "model-00012-of-00001.safetensors",
+    "model.layers.47.self_attn.q_norm.weight": "model-00012-of-00001.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00012-of-00001.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00012-of-00001.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00012-of-00001.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00012-of-00001.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00012-of-00001.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00012-of-00001.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00012-of-00001.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00012-of-00001.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00012-of-00001.safetensors",
+    "model.layers.48.self_attn.k_norm.weight": "model-00012-of-00001.safetensors",
+    "model.layers.48.self_attn.q_norm.weight": "model-00012-of-00001.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00012-of-00001.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00012-of-00001.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00012-of-00001.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00012-of-00001.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00012-of-00001.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00012-of-00001.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00013-of-00001.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00013-of-00001.safetensors",
+    "model.layers.49.self_attn.k_norm.weight": "model-00013-of-00001.safetensors",
+    "model.layers.49.self_attn.q_norm.weight": "model-00013-of-00001.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00013-of-00001.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00013-of-00001.safetensors",
+    "model.layers.50.self_attn.k_norm.weight": "model-00013-of-00001.safetensors",
+    "model.layers.50.self_attn.q_norm.weight": "model-00013-of-00001.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00013-of-00001.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00013-of-00001.safetensors",
+    "model.layers.51.self_attn.k_norm.weight": "model-00013-of-00001.safetensors",
+    "model.layers.51.self_attn.q_norm.weight": "model-00013-of-00001.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00013-of-00001.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00013-of-00001.safetensors",
+    "model.layers.52.self_attn.k_norm.weight": "model-00013-of-00001.safetensors",
+    "model.layers.52.self_attn.q_norm.weight": "model-00013-of-00001.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00013-of-00001.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00013-of-00001.safetensors",
+    "model.layers.53.self_attn.k_norm.weight": "model-00013-of-00001.safetensors",
+    "model.layers.53.self_attn.q_norm.weight": "model-00013-of-00001.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00013-of-00001.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00014-of-00001.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00014-of-00001.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00014-of-00001.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00014-of-00001.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00014-of-00001.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00014-of-00001.safetensors",
+    "model.layers.54.self_attn.k_norm.weight": "model-00014-of-00001.safetensors",
+    "model.layers.54.self_attn.q_norm.weight": "model-00014-of-00001.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00014-of-00001.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00014-of-00001.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00014-of-00001.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00014-of-00001.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00014-of-00001.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00014-of-00001.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00014-of-00001.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00014-of-00001.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00014-of-00001.safetensors",
+    "model.layers.55.self_attn.k_norm.weight": "model-00014-of-00001.safetensors",
+    "model.layers.55.self_attn.q_norm.weight": "model-00014-of-00001.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00014-of-00001.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00014-of-00001.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00014-of-00001.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00014-of-00001.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00014-of-00001.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00014-of-00001.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00014-of-00001.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00014-of-00001.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00014-of-00001.safetensors",
+    "model.layers.56.self_attn.k_norm.weight": "model-00014-of-00001.safetensors",
+    "model.layers.56.self_attn.q_norm.weight": "model-00014-of-00001.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00014-of-00001.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00014-of-00001.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00014-of-00001.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00014-of-00001.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00014-of-00001.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00014-of-00001.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00014-of-00001.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00014-of-00001.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00014-of-00001.safetensors",
+    "model.layers.57.self_attn.k_norm.weight": "model-00014-of-00001.safetensors",
+    "model.layers.57.self_attn.q_norm.weight": "model-00014-of-00001.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00014-of-00001.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00014-of-00001.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00014-of-00001.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00014-of-00001.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00014-of-00001.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00015-of-00001.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00015-of-00001.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00015-of-00001.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00015-of-00001.safetensors",
+    "model.layers.58.self_attn.k_norm.weight": "model-00015-of-00001.safetensors",
+    "model.layers.58.self_attn.q_norm.weight": "model-00015-of-00001.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00015-of-00001.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00015-of-00001.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00015-of-00001.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00015-of-00001.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00015-of-00001.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00015-of-00001.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00015-of-00001.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00015-of-00001.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00015-of-00001.safetensors",
+    "model.layers.59.self_attn.k_norm.weight": "model-00015-of-00001.safetensors",
+    "model.layers.59.self_attn.q_norm.weight": "model-00015-of-00001.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00015-of-00001.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00015-of-00001.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00015-of-00001.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00015-of-00001.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00015-of-00001.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00015-of-00001.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00015-of-00001.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00015-of-00001.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00015-of-00001.safetensors",
+    "model.layers.60.self_attn.k_norm.weight": "model-00015-of-00001.safetensors",
+    "model.layers.60.self_attn.q_norm.weight": "model-00015-of-00001.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00015-of-00001.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00015-of-00001.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00015-of-00001.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00015-of-00001.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00015-of-00001.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00015-of-00001.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00015-of-00001.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00015-of-00001.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00015-of-00001.safetensors",
+    "model.layers.61.self_attn.k_norm.weight": "model-00015-of-00001.safetensors",
+    "model.layers.61.self_attn.q_norm.weight": "model-00015-of-00001.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00015-of-00001.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00015-of-00001.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00015-of-00001.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00015-of-00001.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00015-of-00001.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00015-of-00001.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00016-of-00001.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00016-of-00001.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00016-of-00001.safetensors",
+    "model.layers.62.self_attn.k_norm.weight": "model-00016-of-00001.safetensors",
+    "model.layers.62.self_attn.q_norm.weight": "model-00016-of-00001.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00016-of-00001.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00016-of-00001.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00016-of-00001.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00016-of-00001.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00016-of-00001.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00016-of-00001.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00016-of-00001.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00016-of-00001.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00016-of-00001.safetensors",
+    "model.layers.63.self_attn.k_norm.weight": "model-00016-of-00001.safetensors",
+    "model.layers.63.self_attn.q_norm.weight": "model-00016-of-00001.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00016-of-00001.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00016-of-00001.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00016-of-00001.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00016-of-00001.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00016-of-00001.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00016-of-00001.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00016-of-00001.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4c4f5cd2e69aa1a945034c4a4d5c0867136ad127e955eeea7e78a58c1a040fd
+size 11423410

tokenizer_config.json

@@ -0,0 +1,256 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151669": {
+      "content": "<function=",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151670": {
+      "content": "<parameter=",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151671": {
+      "content": "</parameter>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151672": {
+      "content": "</function>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}