Upload folder using huggingface_hub

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

@@ -1,10 +1,11 @@
 {
+  "_name_or_path": "array/Qwen2.5-VL-MullGRPO",
   "architectures": [
     "Qwen2_5_VLForConditionalGeneration"
   ],
   "attention_dropout": 0.0,
   "auto_map": {
-    "AutoModelForVision2Seq": "mmlatentdiscrete_qwen_vl.Qwen2_5_VLForConditionalGeneration"
+    "AutoModelForVision2Seq": "array/Qwen2.5-VL-MullGRPO--mmlatentdiscrete_qwen_vl.Qwen2_5_VLForConditionalGeneration"
   },
   "bos_token_id": 151643,
   "compress_strategy": "average",
@@ -40,111 +41,23 @@
   "rope_theta": 1000000.0,
   "sliding_window": 32768,
   "stage": "stage2",
-  "text_config": {
-    "_name_or_path": "/usr/local/google/home/arijitray/Documents/final_models/qwen_vl_mulldiscrete_grpo200",
-    "architectures": [
-      "Qwen2_5_VLForConditionalGeneration"
-    ],
-    "attention_dropout": 0.0,
-    "bos_token_id": 151643,
-    "compress_strategy": "average",
-    "dtype": "bfloat16",
-    "eos_token_id": 151645,
-    "hidden_act": "silu",
-    "hidden_size": 3584,
-    "imagelatent_token_id": 151668,
-    "initializer_range": 0.02,
-    "intermediate_size": 18944,
-    "latent_end_id": 151667,
-    "latent_sample_temperature": 2,
-    "latent_size": 4,
-    "latent_start_id": 151666,
-    "latent_token_id": 151665,
-    "layer_types": [
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention",
-      "full_attention"
-    ],
-    "max_position_embeddings": 128000,
-    "max_window_layers": 28,
-    "model_type": "qwen2_5_vl_text",
-    "num_attention_heads": 28,
-    "num_hidden_layers": 28,
-    "num_key_value_heads": 4,
-    "rms_norm_eps": 1e-06,
-    "rope_scaling": {
-      "mrope_section": [
-        16,
-        24,
-        24
-      ],
-      "rope_type": "default",
-      "type": "default"
-    },
-    "rope_theta": 1000000.0,
-    "sliding_window": null,
-    "stage": "stage2",
-    "use_cache": true,
-    "use_latent_projection": false,
-    "use_sliding_window": false,
-    "vision_token_id": 151654,
-    "vocab_size": 151669
-  },
+  "text_config": null,
   "tie_word_embeddings": false,
-  "transformers_version": "4.57.3",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0.dev0",
   "use_cache": true,
   "use_latent_projection": false,
   "use_sliding_window": false,
   "video_token_id": 151656,
   "vision_config": {
-    "depth": 32,
     "dtype": "bfloat16",
-    "fullatt_block_indexes": [
-      7,
-      15,
-      23,
-      31
-    ],
-    "hidden_act": "silu",
     "hidden_size": 1280,
-    "in_channels": 3,
     "in_chans": 3,
     "initializer_range": 0.02,
-    "intermediate_size": 3420,
     "model_type": "qwen2_5_vl",
-    "num_heads": 16,
-    "out_hidden_size": 3584,
-    "patch_size": 14,
-    "spatial_merge_size": 2,
     "spatial_patch_size": 14,
-    "temporal_patch_size": 2,
     "tokens_per_second": 2,
-    "window_size": 112
+    "torch_dtype": "bfloat16"
   },
   "vision_end_token_id": 151653,
   "vision_start_token_id": 151652,

generation_config.json

@@ -8,5 +8,5 @@
   "pad_token_id": 151643,
   "repetition_penalty": 1.05,
   "temperature": 1e-06,
-  "transformers_version": "4.57.3"
+  "transformers_version": "4.49.0.dev0"
 }

model.safetensors.index.json

@@ -1,6 +1,5 @@
 {
   "metadata": {
-    "total_parameters": 8289335296,
     "total_size": 16578670592
   },
   "weight_map": {

preprocessor_config.json

@@ -8,7 +8,7 @@
     0.4578275,
     0.40821073
   ],
-  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_processor_type": "Qwen2_5_VLImageProcessor",
   "image_std": [
     0.26862954,
     0.26130258,

tokenizer_config.json

@@ -227,6 +227,7 @@
     "<|video_pad|>"
   ],
   "bos_token": null,
+  "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 %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",