Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,6 @@ 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
+llm/model.onnx.data filter=lfs diff=lfs merge=lfs -text
+llm/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+visual/model.onnx.data filter=lfs diff=lfs merge=lfs -text

llm/chat_template.jinja

@@ -0,0 +1,120 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

llm/config.json

@@ -0,0 +1,64 @@
+{
+  "model": "qwen3_vl_text",
+  "spec_decode_type": "none",
+  "engine_role": "llm",
+  "edgellm_version": "0.10.0",
+  "vocab_size": 151936,
+  "hidden_size": 2560,
+  "intermediate_size": 9728,
+  "num_hidden_layers": 36,
+  "num_attention_heads": 32,
+  "num_key_value_heads": 8,
+  "head_dim": 128,
+  "max_position_embeddings": 262144,
+  "rope_theta": 5000000.0,
+  "rope_scaling": {
+    "mrope_interleaved": true,
+    "mrope_section": [
+      24,
+      20,
+      20
+    ],
+    "rope_theta": 5000000,
+    "rope_type": "default",
+    "type": "default"
+  },
+  "partial_rotary_factor": 1.0,
+  "num_deepstack_features": 3,
+  "use_vision_bidirectional_attention": false,
+  "rms_norm_eps": 1e-06,
+  "attention_scaling": 0.08838834764831843,
+  "ple_enabled": false,
+  "num_ple_inputs": 0,
+  "ple_hidden_size": 0,
+  "kv_cache_dtype": "fp16",
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      5,
+      11,
+      17
+    ],
+    "depth": 24,
+    "dtype": "float16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "qwen3_vl_vision",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2560,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "image_token_id": 151655,
+  "video_token_id": 151656,
+  "vision_start_token_id": 151652,
+  "vision_end_token_id": 151653
+}

llm/embedding.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:457e1e4d7746de09055ab0f39c3e9041523c47d36bb93cee2eb6b5101336dbe3
+size 777912408

llm/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18d80299bc752e844b94e276973d10d7c5d8f4d17762386d39ef7e7858e342ad
+size 3723297

llm/model.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aa19f2cce29914c61e7c3db3eddc33d1a74fe25c376b9de19ac8da5cca2e687
+size 2653683712

llm/processed_chat_template.json

@@ -0,0 +1,27 @@
+{
+  "model_path": "/data/users/Sakthi/Qwen3-VL-4B-Instruct-model",
+  "roles": {
+    "system": {
+      "prefix": "<|im_start|>system\n",
+      "suffix": "<|im_end|>\n"
+    },
+    "user": {
+      "prefix": "<|im_start|>user\n",
+      "suffix": "<|im_end|>\n"
+    },
+    "assistant": {
+      "prefix": "<|im_start|>assistant\n",
+      "suffix": "<|im_end|>\n"
+    }
+  },
+  "content_types": {
+    "image": {
+      "format": "<|vision_start|><|image_pad|><|vision_end|>"
+    },
+    "video": {
+      "format": "<|vision_start|><|video_pad|><|vision_end|>"
+    }
+  },
+  "generation_prompt": "<|im_start|>assistant\n",
+  "default_system_prompt": ""
+}

llm/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

llm/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "max_pixels": 2097152,
+  "min_pixels": 100352,
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

visual/config.json

@@ -0,0 +1,41 @@
+{
+  "model_type": "qwen3_vl",
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      5,
+      11,
+      17
+    ],
+    "depth": 24,
+    "dtype": "float16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "qwen3_vl_vision",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2560,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_start_token_id": 151652,
+  "vision_end_token_id": 151653,
+  "image_token_id": 151655,
+  "video_token_id": 151656,
+  "vocab_size": 151936,
+  "rope_theta": 5000000,
+  "rope_scaling": {
+    "mrope_interleaved": true,
+    "mrope_section": [
+      24,
+      20,
+      20
+    ],
+    "rope_theta": 5000000,
+    "rope_type": "default",
+    "type": "default"
+  }
+}

visual/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3bb7b638910c9d316ece10c1d47e10298cf2d3e242c0b619c235f261ee2722e
+size 2108339

visual/model.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a80a5f1e4a0b36fca9722dc500b96acdc8a42b3bf6c3a96703fca63201f42ec
+size 830996480

visual/preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "merge_size": 2,
+  "patch_size": 16,
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 2097152,
+    "shortest_edge": 100352
+  },
+  "temporal_patch_size": 2
+}