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 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<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 +1,117 @@
+{% macro render_extra_keys(json_dict, handled_keys) %}
+    {%- if json_dict is mapping %}
+        {%- for json_key in json_dict if json_key not in handled_keys %}
+            {%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}
+                {{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}
+            {%- else %}
+                {{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+{% endmacro %}
+
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+
+{%- if not tools is defined %}
+    {%- set tools = [] %}
+{%- endif %}
+
+{%- if system_message is defined %}
+    {{- "<|im_start|>system\n" + system_message }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- "<|im_start|>system\nYou are Qwen, a helpful AI assistant that can interact with a computer to solve tasks." }}
+    {%- endif %}
+{%- endif %}
+{%- if tools is iterable and tools | length > 0 %}
+    {{- "\n\n# Tools\n\nYou have access to the following functions:\n\n" }}
+    {{- "<tools>" }}
+    {%- for tool in tools %}
+        {%- if tool.function is defined %}
+            {%- set tool = tool.function %}
+        {%- endif %}
+        {{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
+        {%- if tool.description is defined %}
+            {{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
+        {%- endif %}
+        {{- '\n<parameters>' }}
+        {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
+            {%- for param_name, param_fields in tool.parameters.properties|items %}
+                {{- '\n<parameter>' }}
+                {{- '\n<name>' ~ param_name ~ '</name>' }}
+                {%- if param_fields.type is defined %}
+                    {{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
+                {%- endif %}
+                {%- if param_fields.description is defined %}
+                    {{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
+                {%- endif %}
+                {%- set handled_keys = ['name', 'type', 'description'] %}
+                {{- render_extra_keys(param_fields, handled_keys) }}
+                {{- '\n</parameter>' }}
+            {%- endfor %}
+        {%- endif %}
+        {% set handled_keys = ['type', 'properties'] %}
+        {{- render_extra_keys(tool.parameters, handled_keys) }}
+        {{- '\n</parameters>' }}
+        {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
+        {{- render_extra_keys(tool, handled_keys) }}
+        {{- '\n</function>' }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+{%- endif %}
+{%- if system_message is defined %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in loop_messages %}
+    {%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content is defined and message.content is string and message.content | trim | length > 0 %}
+            {{- '\n' + message.content | trim + '\n' }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- 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 | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                    {{- args_value }}
+                    {{- '\n</parameter>\n' }}
+                {%- endfor %}
+            {%- endif %}
+            {{- '</function>\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user\n' }}
+        {%- endif %}
+        {{- '<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>\n' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,406 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "decoder_sparse_step": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 262144,
+  "max_window_layers": 62,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_moe",
+  "moe_intermediate_size": 2560,
+  "norm_topk_prob": true,
+  "num_attention_heads": 96,
+  "num_experts": 160,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 62,
+  "num_key_value_heads": 8,
+  "output_router_logits": false,
+  "qkv_bias": false,
+  "quantization_config": {
+    "algo_config": null,
+    "exclude": [
+      "model.layers.0.self_attn.q_proj",
+      "model.layers.0.self_attn.k_proj",
+      "model.layers.0.self_attn.v_proj",
+      "model.layers.0.self_attn.o_proj",
+      "model.layers.0.mlp.gate",
+      "model.layers.1.self_attn.q_proj",
+      "model.layers.1.self_attn.k_proj",
+      "model.layers.1.self_attn.v_proj",
+      "model.layers.1.self_attn.o_proj",
+      "model.layers.1.mlp.gate",
+      "model.layers.2.self_attn.q_proj",
+      "model.layers.2.self_attn.k_proj",
+      "model.layers.2.self_attn.v_proj",
+      "model.layers.2.self_attn.o_proj",
+      "model.layers.2.mlp.gate",
+      "model.layers.3.self_attn.q_proj",
+      "model.layers.3.self_attn.k_proj",
+      "model.layers.3.self_attn.v_proj",
+      "model.layers.3.self_attn.o_proj",
+      "model.layers.3.mlp.gate",
+      "model.layers.4.self_attn.q_proj",
+      "model.layers.4.self_attn.k_proj",
+      "model.layers.4.self_attn.v_proj",
+      "model.layers.4.self_attn.o_proj",
+      "model.layers.4.mlp.gate",
+      "model.layers.5.self_attn.q_proj",
+      "model.layers.5.self_attn.k_proj",
+      "model.layers.5.self_attn.v_proj",
+      "model.layers.5.self_attn.o_proj",
+      "model.layers.5.mlp.gate",
+      "model.layers.6.self_attn.q_proj",
+      "model.layers.6.self_attn.k_proj",
+      "model.layers.6.self_attn.v_proj",
+      "model.layers.6.self_attn.o_proj",
+      "model.layers.6.mlp.gate",
+      "model.layers.7.self_attn.q_proj",
+      "model.layers.7.self_attn.k_proj",
+      "model.layers.7.self_attn.v_proj",
+      "model.layers.7.self_attn.o_proj",
+      "model.layers.7.mlp.gate",
+      "model.layers.8.self_attn.q_proj",
+      "model.layers.8.self_attn.k_proj",
+      "model.layers.8.self_attn.v_proj",
+      "model.layers.8.self_attn.o_proj",
+      "model.layers.8.mlp.gate",
+      "model.layers.9.self_attn.q_proj",
+      "model.layers.9.self_attn.k_proj",
+      "model.layers.9.self_attn.v_proj",
+      "model.layers.9.self_attn.o_proj",
+      "model.layers.9.mlp.gate",
+      "model.layers.10.self_attn.q_proj",
+      "model.layers.10.self_attn.k_proj",
+      "model.layers.10.self_attn.v_proj",
+      "model.layers.10.self_attn.o_proj",
+      "model.layers.10.mlp.gate",
+      "model.layers.11.self_attn.q_proj",
+      "model.layers.11.self_attn.k_proj",
+      "model.layers.11.self_attn.v_proj",
+      "model.layers.11.self_attn.o_proj",
+      "model.layers.11.mlp.gate",
+      "model.layers.12.self_attn.q_proj",
+      "model.layers.12.self_attn.k_proj",
+      "model.layers.12.self_attn.v_proj",
+      "model.layers.12.self_attn.o_proj",
+      "model.layers.12.mlp.gate",
+      "model.layers.13.self_attn.q_proj",
+      "model.layers.13.self_attn.k_proj",
+      "model.layers.13.self_attn.v_proj",
+      "model.layers.13.self_attn.o_proj",
+      "model.layers.13.mlp.gate",
+      "model.layers.14.self_attn.q_proj",
+      "model.layers.14.self_attn.k_proj",
+      "model.layers.14.self_attn.v_proj",
+      "model.layers.14.self_attn.o_proj",
+      "model.layers.14.mlp.gate",
+      "model.layers.15.self_attn.q_proj",
+      "model.layers.15.self_attn.k_proj",
+      "model.layers.15.self_attn.v_proj",
+      "model.layers.15.self_attn.o_proj",
+      "model.layers.15.mlp.gate",
+      "model.layers.16.self_attn.q_proj",
+      "model.layers.16.self_attn.k_proj",
+      "model.layers.16.self_attn.v_proj",
+      "model.layers.16.self_attn.o_proj",
+      "model.layers.16.mlp.gate",
+      "model.layers.17.self_attn.q_proj",
+      "model.layers.17.self_attn.k_proj",
+      "model.layers.17.self_attn.v_proj",
+      "model.layers.17.self_attn.o_proj",
+      "model.layers.17.mlp.gate",
+      "model.layers.18.self_attn.q_proj",
+      "model.layers.18.self_attn.k_proj",
+      "model.layers.18.self_attn.v_proj",
+      "model.layers.18.self_attn.o_proj",
+      "model.layers.18.mlp.gate",
+      "model.layers.19.self_attn.q_proj",
+      "model.layers.19.self_attn.k_proj",
+      "model.layers.19.self_attn.v_proj",
+      "model.layers.19.self_attn.o_proj",
+      "model.layers.19.mlp.gate",
+      "model.layers.20.self_attn.q_proj",
+      "model.layers.20.self_attn.k_proj",
+      "model.layers.20.self_attn.v_proj",
+      "model.layers.20.self_attn.o_proj",
+      "model.layers.20.mlp.gate",
+      "model.layers.21.self_attn.q_proj",
+      "model.layers.21.self_attn.k_proj",
+      "model.layers.21.self_attn.v_proj",
+      "model.layers.21.self_attn.o_proj",
+      "model.layers.21.mlp.gate",
+      "model.layers.22.self_attn.q_proj",
+      "model.layers.22.self_attn.k_proj",
+      "model.layers.22.self_attn.v_proj",
+      "model.layers.22.self_attn.o_proj",
+      "model.layers.22.mlp.gate",
+      "model.layers.23.self_attn.q_proj",
+      "model.layers.23.self_attn.k_proj",
+      "model.layers.23.self_attn.v_proj",
+      "model.layers.23.self_attn.o_proj",
+      "model.layers.23.mlp.gate",
+      "model.layers.24.self_attn.q_proj",
+      "model.layers.24.self_attn.k_proj",
+      "model.layers.24.self_attn.v_proj",
+      "model.layers.24.self_attn.o_proj",
+      "model.layers.24.mlp.gate",
+      "model.layers.25.self_attn.q_proj",
+      "model.layers.25.self_attn.k_proj",
+      "model.layers.25.self_attn.v_proj",
+      "model.layers.25.self_attn.o_proj",
+      "model.layers.25.mlp.gate",
+      "model.layers.26.self_attn.q_proj",
+      "model.layers.26.self_attn.k_proj",
+      "model.layers.26.self_attn.v_proj",
+      "model.layers.26.self_attn.o_proj",
+      "model.layers.26.mlp.gate",
+      "model.layers.27.self_attn.q_proj",
+      "model.layers.27.self_attn.k_proj",
+      "model.layers.27.self_attn.v_proj",
+      "model.layers.27.self_attn.o_proj",
+      "model.layers.27.mlp.gate",
+      "model.layers.28.self_attn.q_proj",
+      "model.layers.28.self_attn.k_proj",
+      "model.layers.28.self_attn.v_proj",
+      "model.layers.28.self_attn.o_proj",
+      "model.layers.28.mlp.gate",
+      "model.layers.29.self_attn.q_proj",
+      "model.layers.29.self_attn.k_proj",
+      "model.layers.29.self_attn.v_proj",
+      "model.layers.29.self_attn.o_proj",
+      "model.layers.29.mlp.gate",
+      "model.layers.30.self_attn.q_proj",
+      "model.layers.30.self_attn.k_proj",
+      "model.layers.30.self_attn.v_proj",
+      "model.layers.30.self_attn.o_proj",
+      "model.layers.30.mlp.gate",
+      "model.layers.31.self_attn.q_proj",
+      "model.layers.31.self_attn.k_proj",
+      "model.layers.31.self_attn.v_proj",
+      "model.layers.31.self_attn.o_proj",
+      "model.layers.31.mlp.gate",
+      "model.layers.32.self_attn.q_proj",
+      "model.layers.32.self_attn.k_proj",
+      "model.layers.32.self_attn.v_proj",
+      "model.layers.32.self_attn.o_proj",
+      "model.layers.32.mlp.gate",
+      "model.layers.33.self_attn.q_proj",
+      "model.layers.33.self_attn.k_proj",
+      "model.layers.33.self_attn.v_proj",
+      "model.layers.33.self_attn.o_proj",
+      "model.layers.33.mlp.gate",
+      "model.layers.34.self_attn.q_proj",
+      "model.layers.34.self_attn.k_proj",
+      "model.layers.34.self_attn.v_proj",
+      "model.layers.34.self_attn.o_proj",
+      "model.layers.34.mlp.gate",
+      "model.layers.35.self_attn.q_proj",
+      "model.layers.35.self_attn.k_proj",
+      "model.layers.35.self_attn.v_proj",
+      "model.layers.35.self_attn.o_proj",
+      "model.layers.35.mlp.gate",
+      "model.layers.36.self_attn.q_proj",
+      "model.layers.36.self_attn.k_proj",
+      "model.layers.36.self_attn.v_proj",
+      "model.layers.36.self_attn.o_proj",
+      "model.layers.36.mlp.gate",
+      "model.layers.37.self_attn.q_proj",
+      "model.layers.37.self_attn.k_proj",
+      "model.layers.37.self_attn.v_proj",
+      "model.layers.37.self_attn.o_proj",
+      "model.layers.37.mlp.gate",
+      "model.layers.38.self_attn.q_proj",
+      "model.layers.38.self_attn.k_proj",
+      "model.layers.38.self_attn.v_proj",
+      "model.layers.38.self_attn.o_proj",
+      "model.layers.38.mlp.gate",
+      "model.layers.39.self_attn.q_proj",
+      "model.layers.39.self_attn.k_proj",
+      "model.layers.39.self_attn.v_proj",
+      "model.layers.39.self_attn.o_proj",
+      "model.layers.39.mlp.gate",
+      "model.layers.40.self_attn.q_proj",
+      "model.layers.40.self_attn.k_proj",
+      "model.layers.40.self_attn.v_proj",
+      "model.layers.40.self_attn.o_proj",
+      "model.layers.40.mlp.gate",
+      "model.layers.41.self_attn.q_proj",
+      "model.layers.41.self_attn.k_proj",
+      "model.layers.41.self_attn.v_proj",
+      "model.layers.41.self_attn.o_proj",
+      "model.layers.41.mlp.gate",
+      "model.layers.42.self_attn.q_proj",
+      "model.layers.42.self_attn.k_proj",
+      "model.layers.42.self_attn.v_proj",
+      "model.layers.42.self_attn.o_proj",
+      "model.layers.42.mlp.gate",
+      "model.layers.43.self_attn.q_proj",
+      "model.layers.43.self_attn.k_proj",
+      "model.layers.43.self_attn.v_proj",
+      "model.layers.43.self_attn.o_proj",
+      "model.layers.43.mlp.gate",
+      "model.layers.44.self_attn.q_proj",
+      "model.layers.44.self_attn.k_proj",
+      "model.layers.44.self_attn.v_proj",
+      "model.layers.44.self_attn.o_proj",
+      "model.layers.44.mlp.gate",
+      "model.layers.45.self_attn.q_proj",
+      "model.layers.45.self_attn.k_proj",
+      "model.layers.45.self_attn.v_proj",
+      "model.layers.45.self_attn.o_proj",
+      "model.layers.45.mlp.gate",
+      "model.layers.46.self_attn.q_proj",
+      "model.layers.46.self_attn.k_proj",
+      "model.layers.46.self_attn.v_proj",
+      "model.layers.46.self_attn.o_proj",
+      "model.layers.46.mlp.gate",
+      "model.layers.47.self_attn.q_proj",
+      "model.layers.47.self_attn.k_proj",
+      "model.layers.47.self_attn.v_proj",
+      "model.layers.47.self_attn.o_proj",
+      "model.layers.47.mlp.gate",
+      "model.layers.48.self_attn.q_proj",
+      "model.layers.48.self_attn.k_proj",
+      "model.layers.48.self_attn.v_proj",
+      "model.layers.48.self_attn.o_proj",
+      "model.layers.48.mlp.gate",
+      "model.layers.49.self_attn.q_proj",
+      "model.layers.49.self_attn.k_proj",
+      "model.layers.49.self_attn.v_proj",
+      "model.layers.49.self_attn.o_proj",
+      "model.layers.49.mlp.gate",
+      "model.layers.50.self_attn.q_proj",
+      "model.layers.50.self_attn.k_proj",
+      "model.layers.50.self_attn.v_proj",
+      "model.layers.50.self_attn.o_proj",
+      "model.layers.50.mlp.gate",
+      "model.layers.51.self_attn.q_proj",
+      "model.layers.51.self_attn.k_proj",
+      "model.layers.51.self_attn.v_proj",
+      "model.layers.51.self_attn.o_proj",
+      "model.layers.51.mlp.gate",
+      "model.layers.52.self_attn.q_proj",
+      "model.layers.52.self_attn.k_proj",
+      "model.layers.52.self_attn.v_proj",
+      "model.layers.52.self_attn.o_proj",
+      "model.layers.52.mlp.gate",
+      "model.layers.53.self_attn.q_proj",
+      "model.layers.53.self_attn.k_proj",
+      "model.layers.53.self_attn.v_proj",
+      "model.layers.53.self_attn.o_proj",
+      "model.layers.53.mlp.gate",
+      "model.layers.54.self_attn.q_proj",
+      "model.layers.54.self_attn.k_proj",
+      "model.layers.54.self_attn.v_proj",
+      "model.layers.54.self_attn.o_proj",
+      "model.layers.54.mlp.gate",
+      "model.layers.55.self_attn.q_proj",
+      "model.layers.55.self_attn.k_proj",
+      "model.layers.55.self_attn.v_proj",
+      "model.layers.55.self_attn.o_proj",
+      "model.layers.55.mlp.gate",
+      "model.layers.56.self_attn.q_proj",
+      "model.layers.56.self_attn.k_proj",
+      "model.layers.56.self_attn.v_proj",
+      "model.layers.56.self_attn.o_proj",
+      "model.layers.56.mlp.gate",
+      "model.layers.57.self_attn.q_proj",
+      "model.layers.57.self_attn.k_proj",
+      "model.layers.57.self_attn.v_proj",
+      "model.layers.57.self_attn.o_proj",
+      "model.layers.57.mlp.gate",
+      "model.layers.58.self_attn.q_proj",
+      "model.layers.58.self_attn.k_proj",
+      "model.layers.58.self_attn.v_proj",
+      "model.layers.58.self_attn.o_proj",
+      "model.layers.58.mlp.gate",
+      "model.layers.59.self_attn.q_proj",
+      "model.layers.59.self_attn.k_proj",
+      "model.layers.59.self_attn.v_proj",
+      "model.layers.59.self_attn.o_proj",
+      "model.layers.59.mlp.gate",
+      "model.layers.60.self_attn.q_proj",
+      "model.layers.60.self_attn.k_proj",
+      "model.layers.60.self_attn.v_proj",
+      "model.layers.60.self_attn.o_proj",
+      "model.layers.60.mlp.gate",
+      "model.layers.61.self_attn.q_proj",
+      "model.layers.61.self_attn.k_proj",
+      "model.layers.61.self_attn.v_proj",
+      "model.layers.61.self_attn.o_proj",
+      "model.layers.61.mlp.gate",
+      "lm_head"
+    ],
+    "export": {
+      "kv_cache_group": [],
+      "min_kv_scale": 0.0,
+      "pack_method": "reorder",
+      "weight_format": "real_quantized",
+      "weight_merge_groups": null
+    },
+    "global_quant_config": {
+      "bias": null,
+      "input_tensors": {
+        "ch_axis": -1,
+        "dtype": "fp4",
+        "group_size": 32,
+        "is_dynamic": true,
+        "is_scale_quant": false,
+        "mx_element_dtype": null,
+        "observer_cls": "PerBlockMXObserver",
+        "qscheme": "per_group",
+        "round_method": "half_even",
+        "scale_calculation_mode": "even",
+        "scale_format": "e8m0",
+        "scale_type": "float",
+        "symmetric": null
+      },
+      "output_tensors": null,
+      "target_device": null,
+      "weight": {
+        "ch_axis": -1,
+        "dtype": "fp4",
+        "group_size": 32,
+        "is_dynamic": false,
+        "is_scale_quant": false,
+        "mx_element_dtype": null,
+        "observer_cls": "PerBlockMXObserver",
+        "qscheme": "per_group",
+        "round_method": "half_even",
+        "scale_calculation_mode": "even",
+        "scale_format": "e8m0",
+        "scale_type": "float",
+        "symmetric": null
+      }
+    },
+    "kv_cache_post_rope": false,
+    "kv_cache_quant_config": {},
+    "layer_quant_config": {},
+    "layer_type_quant_config": {},
+    "quant_method": "quark",
+    "quant_mode": "eager_mode",
+    "softmax_quant_spec": null,
+    "version": "0.11"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000000,
+  "router_aux_loss_coef": 0.0,
+  "shared_expert_intermediate_size": 0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_qk_norm": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.6"
+}

model-00001-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7ede4a1a7b0c2c9b43669a0d841aea41cf4c3f0b0a0ca9f56c7e8ac8eb8ea62
+size 4995402752

model-00002-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad2c9704e83753bfc2647e4e4a88fff557a4e5a09a34de10d54c024653fa2787
+size 4999710328

model-00003-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbadebaf4241e8f81e6f4aa7363909b8afa73264de6b3ffb04b9291113068dfb
+size 4892089224

model-00004-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2447808d6595dcff886db6fabe11ad0ec578f68dd3e1f3bd5991094a6013ec3c
+size 4995081440

model-00005-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6d722eae19ccce569c491e2bf76439f1f223a50b88aa68243cad68056458e69
+size 4999710176

model-00006-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4fed722599753f0b061bb00ead24a2b694b6308ab4a634d50fa0737bc923eb2
+size 4992337376

model-00007-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94a550720cbc88e0f639bf60656ce1c1e35234477dcd40bea7a816bb7e015e73
+size 4999710168

model-00008-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fba95a610756bdb6b3f232ac30e51a38a8aaa26b3d5b1a51465ee5902729f3f5
+size 4992337480

model-00009-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b445f9a1ea3785419f9b85db9398e996baeb3887c9f2442ab009ca7522c780db
+size 4999710328

model-00010-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:321ca53c2ef6c0ad079d316e552a3763ff0462b6074b279e25f4b34565eaa31d
+size 4917841768

model-00011-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cd2df45c9726824460c291643ce698202bd332cabe40fa828b6b40362ab57eb
+size 4994399208

model-00012-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52ce8cdeab1004d2eeb4ab2b22d2a5e9134c1694caad4c03ae06c60162548efe
+size 4999711296

model-00013-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deb58f4121f9aed36f2352d96e8b4de65c5793f10fb24482f6287a843fb0ade7
+size 4992338504

model-00014-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16a3fc7e62a06cdde5ba09a57a53c79f36241e550c50adff3174d1d9d0ad8ac7
+size 4999711296

model-00015-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ef909f9543a96f0ef848e76c2620c6f3acc0093fd33518db92726da274ecbf2
+size 4992338648

model-00016-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1232432d32f06e04bc99231b7f24244e7abdd00aa12b5f89a21597c75a7c1195
+size 4999711456

model-00017-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23c3ad8dfa60624a79f6b893794045fc54d82ce597534d8fad78a3c4d8e1b46d
+size 4995599016

model-00018-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05f15d816f93353180f5eb68f83b2caa00cbedfdb514596b1261b8dbb5585737
+size 4999711264

model-00019-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2902bfee362daadf9f8b616c2e263e431f5ab10f3db2d5c695c5f8caf3c69aec
+size 4992338504

model-00020-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04671c3e1d0b166b9537ba2e66ebb3d7862edcfc8ce36926523e2f864b8650c5
+size 4999711296

model-00021-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20099d547869326f244bef3685ea59d663eabb9e007b1a2be707f16cf473ff45
+size 4992338552

model-00022-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b1572eefee160b25f9724136270f1d9d446ee71d50946a7d00a4ad61043860
+size 4999711456

model-00023-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48aee7674434815a0be210fe3b831ad5e6445d17714ba6479f795fc8ccc295b8
+size 4967295168

model-00024-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b31f5dbaa0211d868ec1b82bbf17e616a92a535bad994822a4f819fc2d0bab8
+size 4995082496

model-00025-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:819c1587209810cf5ecc3f8bd4f2442594473938478ae152b09c3577627e46b5
+size 4999711296

model-00026-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a2a70f9019c23affc8fecf78142ac90e597cf80038e26c6d0e4f6de74dda454
+size 4992338504

model-00027-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91be7ab3c4073c67f7eaf1b4002867915f053ea097f05b179e184b1dd9ade63c
+size 4999711296

model-00028-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13aa233e8e4d23dd4668b9144dca941f8e3d1e08b0be2c3771813be197b2a4dc
+size 4992338608

model-00029-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24a18858589284b7095eb274e2dd32ad465ed7f8f0029185046445d76c11038d
+size 4999711456

model-00030-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e43ad3da0bc8a5db71cda8511a1fd59fb9e963e9f6150104243b07d86b2bfef5
+size 4917841848

model-00031-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06c91215d418d75d9c016e2879c712efaf52ae810f59fa8e6cf3247ebba66a76
+size 4994399208

model-00032-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b8c58b4af38e6b28b668a05b554fbfe7502ce01acfc23c39fce4adcb6100ab5
+size 4999711296

model-00033-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8506e748702fc530b22beb0de9644a9bd0a5b07cd8549d3373380a03c1297605
+size 4992338504

model-00034-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1f14b0c0e20a391586a6c22d28fbff8ed97111d9e8054898addc0f4fed1ab77
+size 4999711296

model-00035-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60b7a12956e21f8f652c2265269bbebf2f99d123f086ac384e9673c2f56e6b0f
+size 4992338648

model-00036-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7d4213701aefaebf78c4c3db81c6f4b120767e965965b3d449a783e9c80a5d3
+size 4999711456

model-00037-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36215cc22be93fb719a275cfc6c1be3c0923749e58b7d8d2fb9a0ef26d8ac3d0
+size 4995599016

model-00038-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96795821a9b2e55ea34602c12dfbb040fdbbb9d313e584674731eb343b450c39
+size 4999711264

model-00039-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60c22987664f9b539c145062e10c239a6afd2827a340c36b241b82e1abb4a752
+size 4992338504

model-00040-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c187fe8a03db1f113a4e3d06165b73ccd2056973c8b9e5ecd3a6b415f9cf611
+size 4999711296

model-00041-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4c8226b7b9092c75d708f1319becc5ce98bdaf5f3a3b78f2e72b20f7e25beac
+size 4992338552

model-00042-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62cab44099619e02374346ce2981e501f9b840759f796c6491dff8d3762e1594
+size 4999711456

model-00043-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80db4ea21ec13243fc1f7f5aa49df226c6caca4ea2838e6b60a42d772383d4c5
+size 4967295168

model-00044-of-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7e44f986304b3a7ae3b43e29c6aebacf80f68e61c840dafd46570700390eb83
+size 4995082496