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

README.md

@@ -0,0 +1,30 @@
+---
+library_name: mlx
+base_model: XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B
+base_model_relation: finetune
+tags:
+- mimo_v2
+- agentic
+- distillation
+- supervised-fine-tuning
+- code
+- tool-use
+- mlx
+pipeline_tag: image-text-to-text
+---
+
+# AlazarM/MiMo-V2.6-Distill-Qwen-9B-MLX-4bit
+
+This model was converted to MLX format from [`XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B`](https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B)
+using mlx-vlm version **0.7.2**.
+Refer to the [original model card](https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B) for more details on the model.
+
+## Use with mlx
+
+```bash
+pip install -U mlx-vlm
+```
+
+```bash
+python -m mlx_vlm.generate --model AlazarM/MiMo-V2.6-Distill-Qwen-9B-MLX-4bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
+```

chat_template.jinja

@@ -0,0 +1,97 @@
+{%- macro render_value(value) -%}
+    {%- if value is string -%}
+        {{- value -}}
+    {%- else -%}
+        {{- value | tojson(ensure_ascii=False) -}}
+    {%- endif -%}
+{%- endmacro -%}
+
+{%- macro render_content(message_content) -%}
+    {%- if message_content is string -%}
+        {{- message_content -}}
+    {%- elif message_content is iterable -%}
+        {%- for part in message_content -%}
+            {%- if part is not mapping -%}
+                {{- part -}}
+            {%- elif part['type'] == 'image' or 'image' in part or 'image_url' in part -%}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' -}}
+            {%- elif part['type'] == 'audio' or part['type'] == 'input_audio' or 'audio' in part or 'audio_url' in part or 'input_audio' in part -%}
+                {{- '<|mimo_audio_start|><|audio_pad|><|mimo_audio_end|>' -}}
+            {%- elif part['type'] == 'video' or 'video' in part or 'video_url' in part -%}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' -}}
+            {%- elif 'text' in part -%}
+                {{- part['text'] -}}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- endif -%}
+{%- endmacro -%}
+
+{%- macro render_tools(tools) -%}
+    {{- 'You are provided with the following tools:\n\n<tools>' -}}
+    {%- for tool in tools -%}
+        {{- '\n' ~ (tool | tojson(ensure_ascii=False)) -}}
+    {%- endfor -%}
+    {{- '\n</tools>' -}}
+{%- endmacro -%}
+
+{%- macro render_tool_calls(tool_calls) -%}
+    {%- for tool_call in tool_calls -%}
+        {%- if tool_call.function is defined -%}
+            {%- set tool_call = tool_call.function -%}
+        {%- elif tool_call.custom is defined -%}
+            {%- set tool_call = tool_call.custom -%}
+        {%- endif -%}
+        {{- '<tool_call><function=' ~ tool_call.name ~ '>' -}}
+        {%- if tool_call.input is defined and tool_call.input is string -%}
+            {{- tool_call.input -}}
+        {%- elif tool_call.arguments -%}
+            {%- if tool_call.arguments is string -%}
+                {{- tool_call.arguments -}}
+            {%- else -%}
+                {%- for args_name, args_value in tool_call.arguments | items -%}
+                    {{- '<parameter=' ~ args_name ~ '>' ~ render_value(args_value) ~ '</parameter>' -}}
+                {%- endfor -%}
+            {%- endif -%}
+        {%- endif -%}
+        {{- '</function></tool_call>' -}}
+    {%- endfor -%}
+{%- endmacro -%}
+
+{%- macro render_assistant_message(message) -%}
+    {%- generation -%}
+    {%- set content = render_content(message.content) -%}
+    {%- set reasoning = message.reasoning_content if message.reasoning_content is string else '' -%}
+    {{- '<|im_start|>assistant\n<think>' ~ reasoning ~ '</think>' ~ content -}}
+    {%- if message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 -%}
+        {{- render_tool_calls(message.tool_calls) -}}
+    {%- endif -%}
+    {{- '<|im_end|>' -}}
+    {%- endgeneration -%}
+{%- endmacro -%}
+
+{%- if tools is defined and tools is iterable and tools | length > 0 -%}
+    {{- '<|im_start|>system\n' ~ render_tools(tools) ~ '<|im_end|>' -}}
+{%- endif -%}
+
+{%- for message in messages -%}
+    {%- if message.role == 'assistant' -%}
+        {{- render_assistant_message(message) -}}
+    {%- else -%}
+        {%- set body = render_content(message.content) -%}
+        {{- '<|im_start|>' ~ message.role ~ '\n' ~ body -}}
+        {%- if message.tools is defined and message.tools is iterable and message.tools | length > 0 -%}
+            {%- if body -%}
+                {{- '\n\n' -}}
+            {%- endif -%}
+            {{- render_tools(message.tools) -}}
+        {%- endif -%}
+        {{- '<|im_end|>' -}}
+    {%- endif -%}
+{%- endfor -%}
+
+{%- if add_generation_prompt -%}
+    {{- '<|im_start|>assistant\n' -}}
+    {%- if enable_thinking is false -%}
+        {{- '<think></think>' -}}
+    {%- endif -%}
+{%- endif -%}

config.json

@@ -0,0 +1,135 @@
+{
+    "architectures": [
+        "Qwen3_5ForConditionalGeneration"
+    ],
+    "do_sample": true,
+    "eos_token_id": [
+        248046,
+        248044
+    ],
+    "generation_config": {
+        "eos_token_id": [
+            248046,
+            248044
+        ],
+        "do_sample": true,
+        "temperature": 0.6,
+        "top_k": 20,
+        "top_p": 0.95
+    },
+    "image_token_id": 248056,
+    "model_type": "qwen3_5",
+    "quantization": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine"
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine"
+    },
+    "temperature": 0.6,
+    "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": [],
+        "model_type": "qwen3_5_text",
+        "mtp_num_hidden_layers": 1,
+        "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,
+            "rope_type": "default"
+        },
+        "tie_word_embeddings": false,
+        "use_cache": true,
+        "vocab_size": 248320
+    },
+    "tie_word_embeddings": false,
+    "top_k": 20,
+    "top_p": 0.95,
+    "transformers_version": "5.12.1",
+    "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_vision",
+        "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
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "eos_token_id": [
+    248046,
+    248044
+  ],
+  "do_sample": true,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58a44591f48ef6cdcc96ed23cee289ba928b1a127d5cc832dd005c7c5c64b490
+size 5349769710

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f48b6ab909accfc46d50e29afe9115a9eb22849d211e6c39b1a314844e7b7ac0
+size 600449850

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": 16777216,
+    "shortest_edge": 65536
+  },
+  "temporal_patch_size": 2
+}

processor_config.json

@@ -0,0 +1,50 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen3VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_pixels": 16777216,
+    "merge_size": 2,
+    "min_pixels": 65536,
+    "patch_size": 16,
+    "rescale_factor": 0.00392156862745098,
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "fps": 2.0,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "max_pixels": 25165824,
+    "merge_size": 2,
+    "min_frames": 4,
+    "min_pixels": 4096,
+    "patch_size": 16,
+    "rescale_factor": 0.00392156862745098,
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "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": true,
+  "local_files_only": 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+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

video_preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 25165824,
+        "shortest_edge": 4096
+    },
+    "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",
+    "video_processor_type": "Qwen3VLVideoProcessor"
+}