Upload EMOVAForConditionalGeneration

README.md

@@ -159,19 +159,19 @@ model-index:
       name: accuracy
       verified: true
   - task:
-      name: Automatic Speech Recognition
       type: automatic-speech-recognition
+      name: Automatic Speech Recognition
     dataset:
       name: LibriSpeech (clean)
       type: librispeech_asr
       config: clean
       split: test
-      args: 
+      args:
         language: en
     metrics:
-    - name: Test WER
-      type: wer
+    - type: wer
       value: 5.4
+      name: Test WER
 ---
 
 # EMOVA-Qwen-2.5-3B-HF

config.json

@@ -1,52 +1,52 @@
-{
-  "architectures": [
-    "EMOVAForConditionalGeneration"
-  ],
-  "auto_map": {
-    "AutoConfig": "configuration_emova.EMOVAConfig",
-    "AutoModel": "modeling_emova.EMOVAForConditionalGeneration",
-    "AutoModelForCausalLM": "modeling_emova.EMOVAForConditionalGeneration"
-  },
-  "default_system_prompt": "You are a helpful assistant.",
-  "ignore_index": -100,
-  "image_token_index": 155761,
-  "mm_projector_config": {
-    "mlp_depth": 2,
-    "trainable": true,
-    "type": "MLPProjector"
-  },
-  "model_type": "emova",
-  "text_config": {
-    "architectures": [
-      "Qwen2ForCausalLM"
-    ],
-    "bos_token_id": 151643,
-    "eos_token_id": 151645,
-    "hidden_size": 2048,
-    "intermediate_size": 11008,
-    "max_position_embeddings": 32768,
-    "max_window_layers": 70,
-    "model_type": "qwen2",
-    "num_attention_heads": 16,
-    "num_hidden_layers": 36,
-    "num_key_value_heads": 2,
-    "rope_theta": 1000000.0,
-    "sliding_window": null,
-    "tie_word_embeddings": true,
-    "torch_dtype": "float32",
-    "use_sliding_window": false,
-    "vocab_size": 155776
-  },
-  "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.47.1",
-  "vision_config": {
-    "_attn_implementation_autoset": true,
-    "max_pixels": 3211264,
-    "model_type": "qwen2_vl",
-    "pretrained_model_name_or_path": "Emova-ollm/qwen2vit600m",
-    "trainable": true,
-    "type": "Qwen2VisionTower",
-    "unfreeze_mm_vision_tower": true
-  }
-}
+{
+  "_name_or_path": "D:\\temp\\emova_data\\checkpoints\\emova_qwen2_5_3b",
+  "architectures": [
+    "EMOVAForConditionalGeneration"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_emova.EMOVAConfig",
+    "AutoModel": "modeling_emova.EMOVAForConditionalGeneration",
+    "AutoModelForCausalLM": "modeling_emova.EMOVAForConditionalGeneration"
+  },
+  "default_system_prompt": "You are a helpful assistant.",
+  "ignore_index": -100,
+  "image_token_index": 155761,
+  "mm_projector_config": {
+    "mlp_depth": 2,
+    "trainable": true,
+    "type": "MLPProjector"
+  },
+  "model_type": "emova",
+  "text_config": {
+    "architectures": [
+      "Qwen2ForCausalLM"
+    ],
+    "bos_token_id": 151643,
+    "eos_token_id": 151645,
+    "hidden_size": 2048,
+    "intermediate_size": 11008,
+    "max_position_embeddings": 32768,
+    "max_window_layers": 70,
+    "model_type": "qwen2",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 2,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "tie_word_embeddings": true,
+    "torch_dtype": "float32",
+    "use_sliding_window": false,
+    "vocab_size": 155776
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "vision_config": {
+    "max_pixels": 3211264,
+    "model_type": "qwen2_vl",
+    "pretrained_model_name_or_path": "Emova-ollm/qwen2vit600m",
+    "trainable": true,
+    "type": "Qwen2VisionTower",
+    "unfreeze_mm_vision_tower": true
+  }
+}

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 151643,
   "eos_token_id": 151645,
-  "transformers_version": "4.47.1"
+  "transformers_version": "4.44.2"
 }