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 +1,28 @@
+---
+license_name: qwen-research
+license_link: https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct/blob/main/LICENSE
+language:
+- en
+pipeline_tag: image-text-to-text
+tags:
+- multimodal
+- mlx
+library_name: mlx
+base_model: Qwen/Qwen2.5-VL-3B-Instruct
+---
+
+# nervouslyopen/Qwen2.5-VL-3B-Instruct-4bit
+
+This model was converted to MLX format from [`Qwen/Qwen2.5-VL-3B-Instruct`](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct)
+using mlx-vlm version **0.6.3**.
+Refer to the [original model card](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct) for more details on the model.
+
+## Use with mlx
+
+```bash
+pip install -U mlx-vlm
+```
+
+```bash
+python -m mlx_vlm.generate --model nervouslyopen/Qwen2.5-VL-3B-Instruct-4bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
+```

chat_template.jinja

@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% 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 %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

chat_template.json

@@ -0,0 +1,3 @@
+{
+    "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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 %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

config.json

@@ -0,0 +1,87 @@
+{
+    "architectures": [
+        "Qwen2_5_VLForConditionalGeneration"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "do_sample": true,
+    "eos_token_id": [
+        151645,
+        151643
+    ],
+    "generation_config": {
+        "bos_token_id": 151643,
+        "pad_token_id": 151643,
+        "do_sample": true,
+        "eos_token_id": [
+            151645,
+            151643
+        ],
+        "repetition_penalty": 1.05,
+        "temperature": 1e-06,
+        "transformers_version": "4.49.0"
+    },
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "image_token_id": 151655,
+    "initializer_range": 0.02,
+    "intermediate_size": 11008,
+    "max_position_embeddings": 128000,
+    "max_window_layers": 70,
+    "model_type": "qwen2_5_vl",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 2,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine"
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine"
+    },
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+        "type": "mrope",
+        "mrope_section": [
+            16,
+            24,
+            24
+        ]
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": 32768,
+    "temperature": 1e-06,
+    "tie_word_embeddings": true,
+    "transformers_version": "4.41.2",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "video_token_id": 151656,
+    "vision_config": {
+        "depth": 32,
+        "hidden_act": "silu",
+        "hidden_size": 1280,
+        "intermediate_size": 3420,
+        "num_heads": 16,
+        "in_chans": 3,
+        "out_hidden_size": 2048,
+        "patch_size": 14,
+        "spatial_merge_size": 2,
+        "spatial_patch_size": 14,
+        "window_size": 112,
+        "fullatt_block_indexes": [
+            7,
+            15,
+            23,
+            31
+        ],
+        "tokens_per_second": 2,
+        "temporal_patch_size": 2
+    },
+    "vision_end_token_id": 151653,
+    "vision_start_token_id": 151652,
+    "vision_token_id": 151654,
+    "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 151643,
+  "pad_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "repetition_penalty": 1.05,
+  "temperature": 0.000001,
+  "transformers_version": "4.49.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6c75f366b0c54a328b8d64a5458a863cb6102646c8d885015c010f7e4d3ad4c
+size 3073721056

preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "min_pixels": 3136,
+  "max_pixels": 12845056,
+  "patch_size": 14,
+  "temporal_patch_size": 2,
+  "merge_size": 2,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "processor_class": "Qwen2_5_VLProcessor"
+}

processor_config.json

@@ -0,0 +1,50 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "Qwen3VLImageProcessor",
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "max_pixels": 12845056,
+    "merge_size": 2,
+    "min_pixels": 3136,
+    "patch_size": 14,
+    "rescale_factor": 0.00392156862745098,
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen2_5_VLProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "fps": 2.0,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "max_frames": 768,
+    "max_pixels": 12845056,
+    "merge_size": 2,
+    "min_frames": 4,
+    "min_pixels": 3136,
+    "patch_size": 14,
+    "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 sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "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": true,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}