update config (#3)

- Track tokenizer.json with LFS (71413fe40951bad177f1d00c7b8b09decf87116c)
- Add tokenizer.json via LFS (5a65b912323b849b7c150099db8f881cdde50cba)
- update config (a8cb0eadabec912971979c0eb3ae25667adf84de)

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 assets/logo.png filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

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 +1,106 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "vision_start_token_id": 151652,
+  "vision_end_token_id": 151653,
+  "vision_token_id": 151654,
+  "image_token_id": 151655,
+  "video_token_id": 151656,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "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,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "_attn_implementation": "flash_attention_2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "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
+  },
+  "rope_scaling": {
+    "type": "mrope",
+    "mrope_section": [
+      16,
+      24,
+      24
+    ]
+  },
+  "vocab_size": 151936,
+  "num_experts": 2,
+  "experts":[
+    {
+      "hidden_size": 2048,
+      "intermediate_size": 11008,
+      "hidden_act": "silu"
+    },
+    {
+      "hidden_size": 2048,
+      "intermediate_size": 2048,
+      "hidden_act": "silu"
+    }
+  ],
+  "dof_config": {
+      "follow_left_ee_cartesian_pos": 3,
+      "follow_left_ee_rotation": 3,
+      "follow_left_gripper": 1,
+      "follow_right_ee_cartesian_pos": 3,
+      "follow_right_ee_rotation": 3,
+      "follow_right_gripper": 1,
+      "head_actions": 2,
+      "height": 1,
+      "car_pose": 3
+  },
+  "agent_pos_config": {
+    "follow_left_ee_cartesian_pos": 3,
+    "follow_left_ee_rotation": 3,
+    "follow_left_gripper": 1,
+    "follow_right_ee_cartesian_pos": 3,
+    "follow_right_ee_rotation": 3,
+    "follow_right_gripper": 1,
+    "head_actions": 2,
+    "height": 1,
+    "car_pose": 3
+  },
+  "noise_scheduler": {
+    "beta_alpha": 1.5,
+    "beta_beta": 1.0,
+    "s": 0.999,
+    "num_inference_timesteps": 5
+  },
+  "dim_inputs": [2048,2048],
+  "attention_moe": false,
+  "mlp_moe": true
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "vision-understanding", "allow_remote": true}

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"
+}

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"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a5df236d417e062783cda976a6c21955fe386a1dd8fb9aa06f29694a6d3a4de
+size 11826664