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

chat_template.jinja

@@ -0,0 +1,329 @@
+{%- set template_version = "qwen3.6-froggeric-v21.3" %}
+{%- set _tool_format = tool_call_format if tool_call_format is defined else 'xml' %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- set add_vision_id = add_vision_id if add_vision_id is defined else false %}
+{%- set enable_thinking = enable_thinking if enable_thinking is defined else true %}
+{%- set auto_disable_thinking_with_tools = auto_disable_thinking_with_tools if auto_disable_thinking_with_tools is defined else false %}
+{%- set _preserve_thinking = preserve_thinking if preserve_thinking is defined else true %}
+{%- set max_tool_arg_chars = max_tool_arg_chars if max_tool_arg_chars is defined else 0 %}
+{%- set max_tool_response_chars = max_tool_response_chars if max_tool_response_chars is defined else 0 %}
+{%- set _has_tools = (tools is defined and tools and tools is iterable and tools is not mapping) %}
+{%- set ns_state = namespace(thinking=enable_thinking) %}
+{%- if auto_disable_thinking_with_tools and _has_tools %}
+    {%- set ns_state.thinking = false %}
+{%- endif %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if item is mapping %}
+                {%- if item.type == 'image' or 'image' in item or 'image_url' in item %}
+                    {%- if is_system_content %}
+                        {{- raise_exception('System message cannot contain images.') }}
+                    {%- endif %}
+                    {%- if do_vision_count %}
+                        {%- set image_count.value = image_count.value + 1 %}
+                    {%- endif %}
+                    {%- if add_vision_id %}
+                        {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                    {%- endif %}
+                    {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+                {%- elif item.type == 'video' or 'video' in item %}
+                    {%- if is_system_content %}
+                        {{- raise_exception('System message cannot contain videos.') }}
+                    {%- endif %}
+                    {%- if do_vision_count %}
+                        {%- set video_count.value = video_count.value + 1 %}
+                    {%- endif %}
+                    {%- if add_vision_id %}
+                        {{- 'Video ' ~ video_count.value ~ ': ' }}
+                    {%- endif %}
+                    {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+                {%- elif 'text' in item %}
+                    {{- item.text }}
+                {%- else %}
+                    {{- raise_exception('Unexpected item type in content.') }}
+                {%- endif %}
+            {%- else %}
+                {{- item | string }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- set _first_role = messages[0].role %}
+{%- if _first_role == 'system' or _first_role == 'developer' %}
+    {%- set _sys_msg = messages[0] %}
+    {%- set _msgs = messages[1:] %}
+{%- else %}
+    {%- set _sys_msg = none %}
+    {%- set _msgs = messages %}
+{%- endif %}
+{%- set _sc = '' %}
+{%- if _sys_msg is not none %}
+    {%- set _sc = render_content(_sys_msg.content, false, true) | trim %}
+    {%- if '<|think_off|>' in _sc %}
+        {%- set ns_state.thinking = false %}
+        {%- set _sc = _sc.split('<|think_off|>') | join('') | trim %}
+    {%- elif '<|think_on|>' in _sc %}
+        {%- set ns_state.thinking = true %}
+        {%- set _sc = _sc.split('<|think_on|>') | join('') | trim %}
+    {%- endif %}
+{%- endif %}
+{%- if _has_tools %}
+    {{- '<|im_start|>system\n' }}
+    {{- '# Tools\n\nYou have access to the following functions:\n\n<tools>' }}
+    {%- for tool in tools %}
+        {{- '\n' }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- '\n</tools>' }}
+    {%- set tool_instructions %}
+If you choose to call a function ONLY reply in the following format with NO suffix:
+
+{%- if _tool_format == 'json' %}
+<think>
+Brief explanation of tool call
+</think>
+<tool_call>
+{"name": "example_function_name", "arguments": {"example_parameter_1": "value_1", "example_parameter_2": "This is the value for the second parameter"}}
+</tool_call>
+{%- else %}
+<think>
+Brief explanation of tool call
+</think>
+<tool_call>
+<function=example_function_name>
+<parameter=example_parameter_1>
+value_1
+</parameter>
+<parameter=example_parameter_2>
+This is the value for the second parameter
+that can span
+multiple lines
+</parameter>
+</function>
+</tool_call>
+{%- endif %}
+
+<IMPORTANT>
+Reminder:
+- You can use the <think></think> block to plan your next tool call OR to synthesize data and formulate your final response to the user.
+- ALL explanation and reasoning MUST be placed strictly inside the <think></think> block.
+{%- if _tool_format == 'json' %}
+- Function calls MUST follow the specified format: a single JSON object with "name" and "arguments" keys inside <tool_call></tool_call> XML tags.
+{%- else %}
+- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags.
+{%- endif %}
+- If you choose to call a tool, you MUST output the <tool_call> block IMMEDIATELY after thinking, with NO conversational text before it.
+{%- if _tool_format == 'json' %}
+- The <tool_call> tag MUST be at the very beginning of a new line, with NO spaces or indentation before it.
+{%- else %}
+- The <tool_call> and <function> tags MUST be at the very beginning of a new line, with NO spaces or indentation before them.
+{%- endif %}
+- To call multiple functions, output a separate, completely closed <tool_call></tool_call> block for EACH function. Do NOT nest <tool_call> blocks.
+- If you have all necessary data, provide your final answer directly to the user without any tool call.
+</IMPORTANT>
+    {%- endset %}
+    {{- '\n\n' ~ tool_instructions | trim }}
+    {%- if _sc %}
+        {{- '\n\n' + _sc }}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if _sc %}
+        {{- '<|im_start|>system\n' + _sc + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set _last_idx = _msgs | length - 1 %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=_last_idx) %}
+{%- for message in _msgs[::-1] %}
+    {%- set index = (_msgs | length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == 'user' %}
+        {%- set _rc = render_content(message.content, false) | trim %}
+        {%- if not (_rc.startswith('<tool_response>') and _rc.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {%- if _last_idx > 50 %}
+        {%- set ns.last_query_index = _last_idx %}
+    {%- else %}
+        {%- set ns.last_query_index = 0 %}
+    {%- endif %}
+{%- endif %}
+{%- set ns2 = namespace(prev_role='', consecutive_failures=0) %}
+{%- for message in _msgs %}
+    {%- set is_system = (message.role == "system" or message.role == "developer") %}
+    {%- set content = render_content(message.content, true, is_system) | trim %}
+    {%- if is_system or message.role == 'user' %}
+        {%- if '<|think_off|>' in content %}
+            {%- set ns_state.thinking = false %}
+            {%- set content = content.split('<|think_off|>') | join('') | trim %}
+        {%- elif '<|think_on|>' in content %}
+            {%- set ns_state.thinking = true %}
+            {%- set content = content.split('<|think_on|>') | join('') | trim %}
+        {%- endif %}
+    {%- endif %}
+    {%- if is_system %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- elif message.role == 'user' %}
+        {%- set ns2.consecutive_failures = 0 %}
+        {{- '<|im_start|>user\n' + content + '<|im_end|>\n' }}
+    {%- elif message.role == 'assistant' %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- if message.reasoning_content is string %}
+                {%- set reasoning_content = message.reasoning_content %}
+            {%- else %}
+                {%- set reasoning_content = message.reasoning_content | string %}
+            {%- endif %}
+        {%- elif message.thinking is defined and message.thinking is not none %}
+            {%- if message.thinking is string %}
+                {%- set reasoning_content = message.thinking %}
+            {%- else %}
+                {%- set reasoning_content = message.thinking | string %}
+            {%- endif %}
+        {%- else %}
+            {%- set _think_end = '' %}
+            {%- if content.startswith('</think>') %}
+                {%- set _think_end = '</think>' %}
+            {%- elif content.startswith('</thinking>') %}
+                {%- set _think_end = '</thinking>' %}
+            {%- elif '\n</think>' in content %}
+                {%- set _think_end = '\n</think>' %}
+            {%- elif '\n</thinking>' in content %}
+                {%- set _think_end = '\n</thinking>' %}
+            {%- elif '\n</ think>' in content %}
+                {%- set _think_end = '\n</ think>' %}
+            {%- elif '\n</think >' in content %}
+                {%- set _think_end = '\n</think >' %}
+            {%- endif %}
+            {%- if _think_end %}
+                {%- if 'thinking' in _think_end %}
+                    {%- set _think_start = '<thinking>' %}
+                {%- else %}
+                    {%- set _think_start = '<think>' %}
+                {%- endif %}
+                {%- set reasoning_content = content.split(_think_end)[0].rstrip('\n') %}
+                {%- if _think_start in reasoning_content %}
+                    {%- set reasoning_content = reasoning_content.split(_think_start)[-1].lstrip('\n') %}
+                {%- endif %}
+                {%- set content = content.split(_think_end)[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content | trim %}
+        {%- if (_preserve_thinking or loop.index0 > ns.last_query_index) and reasoning_content %}
+            {{- '<|im_start|>assistant\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>assistant\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls is defined and message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined and tool_call.function is not none %}
+                    {%- set tc = tool_call.function %}
+                {%- else %}
+                    {%- set tc = tool_call %}
+                {%- endif %}
+                {%- if _tool_format == 'json' %}
+                    {%- if not loop.first or content | trim %}
+                        {{- '\n\n' }}
+                    {%- endif %}
+                    {%- set _args = '{}' %}
+                    {%- if tc.arguments is defined and tc.arguments is not none %}
+                        {%- if tc.arguments is mapping %}
+                            {%- set _args = tc.arguments | tojson %}
+                        {%- elif tc.arguments is string and tc.arguments %}
+                            {%- set _args = tc.arguments %}
+                        {%- endif %}
+                    {%- endif %}
+                    {{- '<tool_call>\n{"name": ' }}{{- tc.name | tojson }}{{- ', "arguments": ' }}{{- _args }}{{- '}\n</tool_call>' }}
+                {%- else %}
+                    {%- if loop.first %}
+                        {%- if content | trim %}
+                            {{- '\n\n<tool_call>\n<function=' + tc.name + '>\n' }}
+                        {%- else %}
+                            {{- '<tool_call>\n<function=' + tc.name + '>\n' }}
+                        {%- endif %}
+                    {%- else %}
+                        {{- '\n\n<tool_call>\n<function=' + tc.name + '>\n' }}
+                    {%- endif %}
+                    {%- if tc.arguments is defined and tc.arguments is not none %}
+                        {%- if tc.arguments is mapping %}
+                            {%- for args_name, args_value in tc.arguments.items() %}
+                                {{- '<parameter=' + args_name + '>\n' }}
+                                {%- if args_value is mapping or (args_value is sequence and args_value is not string) %}
+                                    {%- set _av = args_value | tojson %}
+                                {%- else %}
+                                    {%- set _av = args_value | string %}
+                                {%- endif %}
+                                {%- if max_tool_arg_chars > 0 and _av | length > max_tool_arg_chars %}
+                                    {{- _av[:max_tool_arg_chars] + '\n[TRUNCATED — original length ' ~ (_av | length | string) ~ ' chars]' }}
+                                {%- else %}
+                                    {{- _av }}
+                                {%- endif %}
+                                {{- '\n</parameter>\n' }}
+                            {%- endfor %}
+                        {%- elif tc.arguments is string and tc.arguments %}
+                            {{- tc.arguments }}
+                        {%- endif %}
+                    {%- endif %}
+                    {{- '</function>\n</tool_call>' }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == 'tool' %}
+        {%- set _content_lower = content | lower %}
+        {%- set _content_head = _content_lower[:80] %}
+        {%- if content | length < 500 and '$ ' not in content and 'took ' not in _content_lower and ('"error":' in _content_head or 'error:' in _content_head or 'err!' in _content_head or 'fatal:' in _content_head or 'exception:' in _content_head or 'traceback' in _content_head or 'command not found' in _content_head or 'invalid syntax' in _content_head or 'failed to' in _content_head) %}
+            {%- set ns2.consecutive_failures = ns2.consecutive_failures + 1 %}
+        {%- else %}
+            {%- set ns2.consecutive_failures = 0 %}
+        {%- endif %}
+        {%- if ns2.prev_role != 'tool' %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {%- if max_tool_response_chars > 0 and content | length > max_tool_response_chars %}
+            {%- set content = content[:max_tool_response_chars] + '\n[TRUNCATED — original length ' ~ (content | length | string) ~ ' chars]' %}
+        {%- endif %}
+        {{- '\n<tool_response>\n' + content }}
+        {%- if ns2.consecutive_failures >= 2 %}
+            {{- '\n\n⚠️ SYSTEM WARNING: ' ~ ns2.consecutive_failures ~ ' consecutive tool errors detected. Your previous approach is incorrect. You MUST use a fundamentally different approach or corrected arguments.' }}
+        {%- elif ns2.consecutive_failures == 1 %}
+            {{- '\n\n⚠️ SYSTEM WARNING: The previous tool call returned an error. Diagnose the failure and retry with completely corrected arguments.' }}
+        {%- endif %}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- else %}
+            {%- set _next_role = _msgs[loop.index0 + 1].role %}
+            {%- if _next_role != 'tool' %}
+                {{- '<|im_end|>\n' }}
+            {%- endif %}
+        {%- endif %}
+    {%- else %}
+        {{- '<|im_start|>user\n[' + message.role + ']: ' + content + '<|im_end|>\n' }}
+    {%- endif %}
+    {%- set ns2.prev_role = message.role %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if not ns_state.thinking %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- elif ns2.consecutive_failures >= 2 %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,500 @@
+{
+  "architectures": [
+    "Qwen3_5ForConditionalGeneration"
+  ],
+  "image_token_id": 248056,
+  "model_type": "qwen3_5",
+  "pad_token_id": 248055,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_output_gate": true,
+    "bos_token_id": null,
+    "dtype": "bfloat16",
+    "eos_token_id": 248044,
+    "full_attention_interval": 4,
+    "head_dim": 256,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 12288,
+    "layer_types": [
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention"
+    ],
+    "linear_conv_kernel_dim": 4,
+    "linear_key_head_dim": 128,
+    "linear_num_key_heads": 16,
+    "linear_num_value_heads": 32,
+    "linear_value_head_dim": 128,
+    "mamba_ssm_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "mlp_only_layers": [],
+    "mtp_num_hidden_layers": 0,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 4,
+    "pad_token_id": null,
+    "partial_rotary_factor": 0.25,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        11,
+        11,
+        10
+      ],
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 10000000,
+      "type": "default"
+    },
+    "tie_word_embeddings": false,
+    "use_cache": true,
+    "vocab_size": 248320,
+    "model_type": "qwen3_5_text"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.3.0.dev0",
+  "unsloth_fixed": true,
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 27,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_5",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 4096,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053,
+  "eos_token_id": 248044,
+  "quantization": {
+    "group_size": 64,
+    "bits": 6,
+    "mode": "affine",
+    "language_model.model.layers.12.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.12.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.16.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.16.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.17.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.17.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.18.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.18.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.19.mlp.down_proj": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.19.self_attn.k_proj": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.19.self_attn.o_proj": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.19.self_attn.v_proj": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.2.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.2.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.20.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.20.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.21.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.21.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.22.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.22.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.30.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.30.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.31.mlp.down_proj": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.31.mlp.gate_proj": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.31.mlp.up_proj": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.31.self_attn.k_proj": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.31.self_attn.o_proj": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.31.self_attn.q_proj": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.31.self_attn.v_proj": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.5.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.5.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.6.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.6.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.7.self_attn.k_proj": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.8.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.8.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.9.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.9.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    }
+  },
+  "quantization_config": {
+    "group_size": 64,
+    "bits": 6,
+    "mode": "affine",
+    "language_model.model.layers.12.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.12.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.16.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.16.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.17.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.17.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.18.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.18.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.19.mlp.down_proj": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.19.self_attn.k_proj": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.19.self_attn.o_proj": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.19.self_attn.v_proj": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.2.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.2.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.20.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.20.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.21.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.21.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.22.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.22.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.30.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.30.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.31.mlp.down_proj": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.31.mlp.gate_proj": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.31.mlp.up_proj": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.31.self_attn.k_proj": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.31.self_attn.o_proj": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.31.self_attn.q_proj": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.31.self_attn.v_proj": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.5.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.5.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.6.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.6.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.7.self_attn.k_proj": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.8.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.8.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.9.linear_attn.in_proj_a": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    },
+    "language_model.model.layers.9.linear_attn.in_proj_b": {
+      "bits": 8,
+      "group_size": 64,
+      "mode": "affine"
+    }
+  }
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 248044,
+  "transformers_version": "5.3.0",
+  "use_cache": true
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9be4d59c03840adb9ab0e595f547f6feac86c007ea8d1db35aecc3f21c3419fd
+size 5016494438

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f88aacc5d070e550cb407aef384e3220ba5ea8b057d152ca88220e3964c2bc04
+size 3245113911

oq_imatrix_report.json

@@ -0,0 +1,361 @@
+{
+  "enabled": true,
+  "cache_path": "/Users/matthew/.omlx/models/.oqe_imatrix/OxCoder-9B-dd258feeab24-s128-l512.npz",
+  "cache_reused": false,
+  "entry_count": 248,
+  "calib_dataset": "oqe_code_multilingual",
+  "collection": {
+    "dataset": "oqe_code_multilingual",
+    "requested_samples": 128,
+    "seq_length": 512,
+    "adaptive": true,
+    "adaptive_step_samples": 128,
+    "adaptive_max_samples": 1024,
+    "available_samples": 1024,
+    "micro_batch_size": 26,
+    "micro_batches": 5,
+    "batch_plan": {
+      "micro_batch_size": 26,
+      "estimated_sample_bytes": 8388608,
+      "capture_budget_bytes": 219486693,
+      "system_available_bytes": 27898888192,
+      "metal_available_bytes": 30146330588,
+      "live_available_bytes": 27898888192,
+      "model_bytes": 5950218862,
+      "remaining_available_bytes": 21948669330,
+      "fits_one_sample": true,
+      "hidden_size": 4096,
+      "num_experts": 0,
+      "top_k": 1,
+      "gemma4_state_bytes": 0,
+      "num_hidden_layers": 32,
+      "num_kv_shared_layers": 0,
+      "per_layer_input_size": 0
+    },
+    "processed_samples": 128,
+    "model_class": "mlx_vlm.models.qwen3_5.qwen3_5.Model",
+    "layer_model_class": "mlx_vlm.models.qwen3_5.language.Qwen3_5Model",
+    "layer_model_type": "qwen3_5_text",
+    "layer_count": 32,
+    "layer_state_kind": "generic",
+    "successful_layer_forwards": 160,
+    "skipped_layer_forwards": 0,
+    "mtp_head_forwards": 0,
+    "installed_modules": 359,
+    "capture_module_classes": {
+      "Linear": 110,
+      "QuantizedLinear": 249
+    },
+    "switch_capture_modules": 0,
+    "requires_expert_counts": false,
+    "coverage_sufficient": true,
+    "collection_sufficient": true,
+    "coverage": {
+      "has_expert_counts": false,
+      "expert_modules": 0,
+      "total_experts": 0,
+      "active_experts": 0,
+      "zero_count_experts": 0,
+      "active_ratio": 1.0,
+      "min_count": 0,
+      "p05_count": 0.0,
+      "p10_count": 0.0,
+      "median_count": 0.0,
+      "max_count": 0,
+      "min_required_count": 16,
+      "required_percentile": 5
+    },
+    "rounds": [
+      {
+        "processed_samples": 128,
+        "coverage_sufficient": true,
+        "collection_sufficient": true,
+        "coverage": {
+          "has_expert_counts": false,
+          "expert_modules": 0,
+          "total_experts": 0,
+          "active_experts": 0,
+          "zero_count_experts": 0,
+          "active_ratio": 1.0,
+          "min_count": 0,
+          "p05_count": 0.0,
+          "p10_count": 0.0,
+          "median_count": 0.0,
+          "max_count": 0,
+          "min_required_count": 16,
+          "required_percentile": 5
+        }
+      }
+    ]
+  },
+  "expert_coverage": {
+    "has_expert_counts": false,
+    "expert_modules": 0,
+    "total_experts": 0,
+    "active_experts": 0,
+    "zero_count_experts": 0,
+    "active_ratio": 1.0,
+    "min_count": 0,
+    "p05_count": 0.0,
+    "p10_count": 0.0,
+    "median_count": 0.0,
+    "max_count": 0,
+    "min_required_count": 16,
+    "required_percentile": 5
+  },
+  "applied": [
+    "language_model.model.layers.0.linear_attn.in_proj_a",
+    "language_model.model.layers.0.linear_attn.in_proj_b",
+    "language_model.model.layers.0.linear_attn.in_proj_qkv",
+    "language_model.model.layers.0.linear_attn.in_proj_z",
+    "language_model.model.layers.0.linear_attn.out_proj",
+    "language_model.model.layers.0.mlp.down_proj",
+    "language_model.model.layers.0.mlp.gate_proj",
+    "language_model.model.layers.0.mlp.up_proj",
+    "language_model.model.layers.1.linear_attn.in_proj_a",
+    "language_model.model.layers.1.linear_attn.in_proj_b",
+    "language_model.model.layers.1.linear_attn.in_proj_qkv",
+    "language_model.model.layers.1.linear_attn.in_proj_z",
+    "language_model.model.layers.1.linear_attn.out_proj",
+    "language_model.model.layers.1.mlp.down_proj",
+    "language_model.model.layers.1.mlp.gate_proj",
+    "language_model.model.layers.1.mlp.up_proj",
+    "language_model.model.layers.10.linear_attn.in_proj_a",
+    "language_model.model.layers.10.linear_attn.in_proj_b",
+    "language_model.model.layers.10.linear_attn.in_proj_qkv",
+    "language_model.model.layers.10.linear_attn.in_proj_z",
+    "language_model.model.layers.10.linear_attn.out_proj",
+    "language_model.model.layers.10.mlp.down_proj",
+    "language_model.model.layers.10.mlp.gate_proj",
+    "language_model.model.layers.10.mlp.up_proj",
+    "language_model.model.layers.11.mlp.down_proj",
+    "language_model.model.layers.11.mlp.gate_proj",
+    "language_model.model.layers.11.mlp.up_proj",
+    "language_model.model.layers.11.self_attn.k_proj",
+    "language_model.model.layers.11.self_attn.o_proj",
+    "language_model.model.layers.11.self_attn.q_proj",
+    "language_model.model.layers.11.self_attn.v_proj",
+    "language_model.model.layers.12.linear_attn.in_proj_a",
+    "language_model.model.layers.12.linear_attn.in_proj_b",
+    "language_model.model.layers.12.linear_attn.in_proj_qkv",
+    "language_model.model.layers.12.linear_attn.in_proj_z",
+    "language_model.model.layers.12.linear_attn.out_proj",
+    "language_model.model.layers.12.mlp.down_proj",
+    "language_model.model.layers.12.mlp.gate_proj",
+    "language_model.model.layers.12.mlp.up_proj",
+    "language_model.model.layers.13.linear_attn.in_proj_a",
+    "language_model.model.layers.13.linear_attn.in_proj_b",
+    "language_model.model.layers.13.linear_attn.in_proj_qkv",
+    "language_model.model.layers.13.linear_attn.in_proj_z",
+    "language_model.model.layers.13.linear_attn.out_proj",
+    "language_model.model.layers.13.mlp.down_proj",
+    "language_model.model.layers.13.mlp.gate_proj",
+    "language_model.model.layers.13.mlp.up_proj",
+    "language_model.model.layers.14.linear_attn.in_proj_a",
+    "language_model.model.layers.14.linear_attn.in_proj_b",
+    "language_model.model.layers.14.linear_attn.in_proj_qkv",
+    "language_model.model.layers.14.linear_attn.in_proj_z",
+    "language_model.model.layers.14.linear_attn.out_proj",
+    "language_model.model.layers.14.mlp.down_proj",
+    "language_model.model.layers.14.mlp.gate_proj",
+    "language_model.model.layers.14.mlp.up_proj",
+    "language_model.model.layers.15.mlp.down_proj",
+    "language_model.model.layers.15.mlp.gate_proj",
+    "language_model.model.layers.15.mlp.up_proj",
+    "language_model.model.layers.15.self_attn.k_proj",
+    "language_model.model.layers.15.self_attn.o_proj",
+    "language_model.model.layers.15.self_attn.q_proj",
+    "language_model.model.layers.15.self_attn.v_proj",
+    "language_model.model.layers.16.linear_attn.in_proj_a",
+    "language_model.model.layers.16.linear_attn.in_proj_b",
+    "language_model.model.layers.16.linear_attn.in_proj_qkv",
+    "language_model.model.layers.16.linear_attn.in_proj_z",
+    "language_model.model.layers.16.linear_attn.out_proj",
+    "language_model.model.layers.16.mlp.down_proj",
+    "language_model.model.layers.16.mlp.gate_proj",
+    "language_model.model.layers.16.mlp.up_proj",
+    "language_model.model.layers.17.linear_attn.in_proj_a",
+    "language_model.model.layers.17.linear_attn.in_proj_b",
+    "language_model.model.layers.17.linear_attn.in_proj_qkv",
+    "language_model.model.layers.17.linear_attn.in_proj_z",
+    "language_model.model.layers.17.linear_attn.out_proj",
+    "language_model.model.layers.17.mlp.down_proj",
+    "language_model.model.layers.17.mlp.gate_proj",
+    "language_model.model.layers.17.mlp.up_proj",
+    "language_model.model.layers.18.linear_attn.in_proj_a",
+    "language_model.model.layers.18.linear_attn.in_proj_b",
+    "language_model.model.layers.18.linear_attn.in_proj_qkv",
+    "language_model.model.layers.18.linear_attn.in_proj_z",
+    "language_model.model.layers.18.linear_attn.out_proj",
+    "language_model.model.layers.18.mlp.down_proj",
+    "language_model.model.layers.18.mlp.gate_proj",
+    "language_model.model.layers.18.mlp.up_proj",
+    "language_model.model.layers.19.mlp.down_proj",
+    "language_model.model.layers.19.mlp.gate_proj",
+    "language_model.model.layers.19.mlp.up_proj",
+    "language_model.model.layers.19.self_attn.k_proj",
+    "language_model.model.layers.19.self_attn.o_proj",
+    "language_model.model.layers.19.self_attn.q_proj",
+    "language_model.model.layers.19.self_attn.v_proj",
+    "language_model.model.layers.2.linear_attn.in_proj_a",
+    "language_model.model.layers.2.linear_attn.in_proj_b",
+    "language_model.model.layers.2.linear_attn.in_proj_qkv",
+    "language_model.model.layers.2.linear_attn.in_proj_z",
+    "language_model.model.layers.2.linear_attn.out_proj",
+    "language_model.model.layers.2.mlp.down_proj",
+    "language_model.model.layers.2.mlp.gate_proj",
+    "language_model.model.layers.2.mlp.up_proj",
+    "language_model.model.layers.20.linear_attn.in_proj_a",
+    "language_model.model.layers.20.linear_attn.in_proj_b",
+    "language_model.model.layers.20.linear_attn.in_proj_qkv",
+    "language_model.model.layers.20.linear_attn.in_proj_z",
+    "language_model.model.layers.20.linear_attn.out_proj",
+    "language_model.model.layers.20.mlp.down_proj",
+    "language_model.model.layers.20.mlp.gate_proj",
+    "language_model.model.layers.20.mlp.up_proj",
+    "language_model.model.layers.21.linear_attn.in_proj_a",
+    "language_model.model.layers.21.linear_attn.in_proj_b",
+    "language_model.model.layers.21.linear_attn.in_proj_qkv",
+    "language_model.model.layers.21.linear_attn.in_proj_z",
+    "language_model.model.layers.21.linear_attn.out_proj",
+    "language_model.model.layers.21.mlp.down_proj",
+    "language_model.model.layers.21.mlp.gate_proj",
+    "language_model.model.layers.21.mlp.up_proj",
+    "language_model.model.layers.22.linear_attn.in_proj_a",
+    "language_model.model.layers.22.linear_attn.in_proj_b",
+    "language_model.model.layers.22.linear_attn.in_proj_qkv",
+    "language_model.model.layers.22.linear_attn.in_proj_z",
+    "language_model.model.layers.22.linear_attn.out_proj",
+    "language_model.model.layers.22.mlp.down_proj",
+    "language_model.model.layers.22.mlp.gate_proj",
+    "language_model.model.layers.22.mlp.up_proj",
+    "language_model.model.layers.23.mlp.down_proj",
+    "language_model.model.layers.23.mlp.gate_proj",
+    "language_model.model.layers.23.mlp.up_proj",
+    "language_model.model.layers.23.self_attn.k_proj",
+    "language_model.model.layers.23.self_attn.o_proj",
+    "language_model.model.layers.23.self_attn.q_proj",
+    "language_model.model.layers.23.self_attn.v_proj",
+    "language_model.model.layers.24.linear_attn.in_proj_a",
+    "language_model.model.layers.24.linear_attn.in_proj_b",
+    "language_model.model.layers.24.linear_attn.in_proj_qkv",
+    "language_model.model.layers.24.linear_attn.in_proj_z",
+    "language_model.model.layers.24.linear_attn.out_proj",
+    "language_model.model.layers.24.mlp.down_proj",
+    "language_model.model.layers.24.mlp.gate_proj",
+    "language_model.model.layers.24.mlp.up_proj",
+    "language_model.model.layers.25.linear_attn.in_proj_a",
+    "language_model.model.layers.25.linear_attn.in_proj_b",
+    "language_model.model.layers.25.linear_attn.in_proj_qkv",
+    "language_model.model.layers.25.linear_attn.in_proj_z",
+    "language_model.model.layers.25.linear_attn.out_proj",
+    "language_model.model.layers.25.mlp.down_proj",
+    "language_model.model.layers.25.mlp.gate_proj",
+    "language_model.model.layers.25.mlp.up_proj",
+    "language_model.model.layers.26.linear_attn.in_proj_a",
+    "language_model.model.layers.26.linear_attn.in_proj_b",
+    "language_model.model.layers.26.linear_attn.in_proj_qkv",
+    "language_model.model.layers.26.linear_attn.in_proj_z",
+    "language_model.model.layers.26.linear_attn.out_proj",
+    "language_model.model.layers.26.mlp.down_proj",
+    "language_model.model.layers.26.mlp.gate_proj",
+    "language_model.model.layers.26.mlp.up_proj",
+    "language_model.model.layers.27.mlp.down_proj",
+    "language_model.model.layers.27.mlp.gate_proj",
+    "language_model.model.layers.27.mlp.up_proj",
+    "language_model.model.layers.27.self_attn.k_proj",
+    "language_model.model.layers.27.self_attn.o_proj",
+    "language_model.model.layers.27.self_attn.q_proj",
+    "language_model.model.layers.27.self_attn.v_proj",
+    "language_model.model.layers.28.linear_attn.in_proj_a",
+    "language_model.model.layers.28.linear_attn.in_proj_b",
+    "language_model.model.layers.28.linear_attn.in_proj_qkv",
+    "language_model.model.layers.28.linear_attn.in_proj_z",
+    "language_model.model.layers.28.linear_attn.out_proj",
+    "language_model.model.layers.28.mlp.down_proj",
+    "language_model.model.layers.28.mlp.gate_proj",
+    "language_model.model.layers.28.mlp.up_proj",
+    "language_model.model.layers.29.linear_attn.in_proj_a",
+    "language_model.model.layers.29.linear_attn.in_proj_b",
+    "language_model.model.layers.29.linear_attn.in_proj_qkv",
+    "language_model.model.layers.29.linear_attn.in_proj_z",
+    "language_model.model.layers.29.linear_attn.out_proj",
+    "language_model.model.layers.29.mlp.down_proj",
+    "language_model.model.layers.29.mlp.gate_proj",
+    "language_model.model.layers.29.mlp.up_proj",
+    "language_model.model.layers.3.mlp.down_proj",
+    "language_model.model.layers.3.mlp.gate_proj",
+    "language_model.model.layers.3.mlp.up_proj",
+    "language_model.model.layers.3.self_attn.k_proj",
+    "language_model.model.layers.3.self_attn.o_proj",
+    "language_model.model.layers.3.self_attn.q_proj",
+    "language_model.model.layers.3.self_attn.v_proj",
+    "language_model.model.layers.30.linear_attn.in_proj_a",
+    "language_model.model.layers.30.linear_attn.in_proj_b",
+    "language_model.model.layers.30.linear_attn.in_proj_qkv",
+    "language_model.model.layers.30.linear_attn.in_proj_z",
+    "language_model.model.layers.30.linear_attn.out_proj",
+    "language_model.model.layers.30.mlp.down_proj",
+    "language_model.model.layers.30.mlp.gate_proj",
+    "language_model.model.layers.30.mlp.up_proj",
+    "language_model.model.layers.31.mlp.down_proj",
+    "language_model.model.layers.31.mlp.gate_proj",
+    "language_model.model.layers.31.mlp.up_proj",
+    "language_model.model.layers.31.self_attn.k_proj",
+    "language_model.model.layers.31.self_attn.o_proj",
+    "language_model.model.layers.31.self_attn.q_proj",
+    "language_model.model.layers.31.self_attn.v_proj",
+    "language_model.model.layers.4.linear_attn.in_proj_a",
+    "language_model.model.layers.4.linear_attn.in_proj_b",
+    "language_model.model.layers.4.linear_attn.in_proj_qkv",
+    "language_model.model.layers.4.linear_attn.in_proj_z",
+    "language_model.model.layers.4.linear_attn.out_proj",
+    "language_model.model.layers.4.mlp.down_proj",
+    "language_model.model.layers.4.mlp.gate_proj",
+    "language_model.model.layers.4.mlp.up_proj",
+    "language_model.model.layers.5.linear_attn.in_proj_a",
+    "language_model.model.layers.5.linear_attn.in_proj_b",
+    "language_model.model.layers.5.linear_attn.in_proj_qkv",
+    "language_model.model.layers.5.linear_attn.in_proj_z",
+    "language_model.model.layers.5.linear_attn.out_proj",
+    "language_model.model.layers.5.mlp.down_proj",
+    "language_model.model.layers.5.mlp.gate_proj",
+    "language_model.model.layers.5.mlp.up_proj",
+    "language_model.model.layers.6.linear_attn.in_proj_a",
+    "language_model.model.layers.6.linear_attn.in_proj_b",
+    "language_model.model.layers.6.linear_attn.in_proj_qkv",
+    "language_model.model.layers.6.linear_attn.in_proj_z",
+    "language_model.model.layers.6.linear_attn.out_proj",
+    "language_model.model.layers.6.mlp.down_proj",
+    "language_model.model.layers.6.mlp.gate_proj",
+    "language_model.model.layers.6.mlp.up_proj",
+    "language_model.model.layers.7.mlp.down_proj",
+    "language_model.model.layers.7.mlp.gate_proj",
+    "language_model.model.layers.7.mlp.up_proj",
+    "language_model.model.layers.7.self_attn.k_proj",
+    "language_model.model.layers.7.self_attn.o_proj",
+    "language_model.model.layers.7.self_attn.q_proj",
+    "language_model.model.layers.7.self_attn.v_proj",
+    "language_model.model.layers.8.linear_attn.in_proj_a",
+    "language_model.model.layers.8.linear_attn.in_proj_b",
+    "language_model.model.layers.8.linear_attn.in_proj_qkv",
+    "language_model.model.layers.8.linear_attn.in_proj_z",
+    "language_model.model.layers.8.linear_attn.out_proj",
+    "language_model.model.layers.8.mlp.down_proj",
+    "language_model.model.layers.8.mlp.gate_proj",
+    "language_model.model.layers.8.mlp.up_proj",
+    "language_model.model.layers.9.linear_attn.in_proj_a",
+    "language_model.model.layers.9.linear_attn.in_proj_b",
+    "language_model.model.layers.9.linear_attn.in_proj_qkv",
+    "language_model.model.layers.9.linear_attn.in_proj_z",
+    "language_model.model.layers.9.linear_attn.out_proj",
+    "language_model.model.layers.9.mlp.down_proj",
+    "language_model.model.layers.9.mlp.gate_proj",
+    "language_model.model.layers.9.mlp.up_proj"
+  ],
+  "missing": [
+    "language_model.lm_head"
+  ],
+  "mismatched": [],
+  "zero_count_experts": 0
+}

preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+  "size": {
+    "longest_edge": 16777216,
+    "shortest_edge": 65536
+  },
+  "patch_size": 16,
+  "temporal_patch_size": 2,
+  "merge_size": 2,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "Qwen3VLProcessor",
+  "image_processor_type": "Qwen2VLImageProcessorFast"
+}

processor_config.json

@@ -0,0 +1,63 @@
+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessorFast",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2TokenizerFast",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}