Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ 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
+0223_0350_llava_one_vision_llava_qwen_lora_ov_32f_llava_onevision_model_args_8ff049/vsibench.json filter=lfs diff=lfs merge=lfs -text
+0223_0351_llava_one_vision_llava_qwen_lora_ov_32f_llava_onevision_model_args_1ad6e5/vsibench.json filter=lfs diff=lfs merge=lfs -text
+0223_2055_llava_one_vision_llava_qwen_lora_ov_32f_llava_onevision_model_args_2229cf/vsibench.json filter=lfs diff=lfs merge=lfs -text
+0223_2055_llava_one_vision_llava_qwen_lora_ov_32f_llava_onevision_model_args_3f39f5/vsibench.json filter=lfs diff=lfs merge=lfs -text

0223_0350_llava_one_vision_llava_qwen_lora_ov_32f_llava_onevision_model_args_8ff049/results.json

@@ -0,0 +1,112 @@
+{
+    "results": {
+        "vsibench": {
+            "alias": "vsibench",
+            "vsibench_score,none": 48.56221772781847,
+            "vsibench_score_stderr,none": "N/A"
+        }
+    },
+    "group_subtasks": {
+        "vsibench": []
+    },
+    "configs": {
+        "vsibench": {
+            "task": "vsibench",
+            "dataset_path": "nyu-visionx/VSI-Bench",
+            "dataset_kwargs": {
+                "token": true
+            },
+            "test_split": "test",
+            "full_docs": false,
+            "process_results_use_image": false,
+            "process_docs": "<function process_docs at 0x4002f1dc4af0>",
+            "doc_to_visual": "<function vsibench_doc_to_visual at 0x4002f1dc51b0>",
+            "doc_to_text": "<function vsibench_doc_to_text at 0x4002f1dc5750>",
+            "doc_to_target": "ground_truth",
+            "process_results": "<function vsibench_process_results at 0x4002f1dc65f0>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "num_fewshot": 0,
+            "metric_list": [
+                {
+                    "metric": "vsibench_score",
+                    "aggregation": "<function vsibench_aggregate_results at 0x4002f1dc6f80>",
+                    "higher_is_better": true
+                }
+            ],
+            "output_type": "generate_until",
+            "generation_kwargs": {
+                "max_new_tokens": 16,
+                "temperature": 0.0,
+                "top_p": 1.0,
+                "num_beams": 1,
+                "do_sample": false,
+                "until": [
+                    "\n\n"
+                ]
+            },
+            "repeats": 1,
+            "should_decontaminate": false,
+            "metadata": [
+                {
+                    "version": 0.0
+                }
+            ],
+            "lmms_eval_specific_kwargs": {
+                "default": {
+                    "pre_prompt": "",
+                    "mca_post_prompt": "Answer with the option's letter from the given choices directly.",
+                    "na_post_prompt": "Please answer the question using a single word or phrase."
+                },
+                "gemini_api": {
+                    "pre_prompt": "",
+                    "mca_post_prompt": "Answer with the option's letter from the given choices directly.",
+                    "na_post_prompt": "Do not response anything other than a single number!"
+                },
+                "gpt4v": {
+                    "pre_prompt": "",
+                    "mca_post_prompt": "Answer with the option's letter from the given choices directly.",
+                    "na_post_prompt": "Do not response anything other than a single number!"
+                },
+                "pre_prompt": "",
+                "mca_post_prompt": "Answer with the option's letter from the given choices directly.",
+                "na_post_prompt": "Please answer the question using a single word or phrase."
+            }
+        }
+    },
+    "versions": {
+        "vsibench": "Yaml"
+    },
+    "n-shot": {
+        "vsibench": 0
+    },
+    "higher_is_better": {
+        "vsibench": {
+            "vsibench_score": true
+        }
+    },
+    "n-samples": {
+        "vsibench": {
+            "original": 5130,
+            "effective": 5130
+        }
+    },
+    "config": {
+        "model": "llava_onevision",
+        "model_args": "pretrained=/scratch/08367/zhiwen/work_dirs/llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-base_lora_vsibench_02_23,attn_implementation=flash_attention_2,conv_template=qwen_1_5,model_name=llava_qwen_lora,max_frames_num=32,model_base=LLaVA-NeXT/checkpoints/LLaVA-Video-7B-Qwen2",
+        "batch_size": "1",
+        "batch_sizes": [],
+        "device": null,
+        "use_cache": null,
+        "limit": null,
+        "bootstrap_iters": 100000,
+        "gen_kwargs": "",
+        "random_seed": 0,
+        "numpy_seed": 1234,
+        "torch_seed": 1234,
+        "fewshot_seed": 1234
+    },
+    "git_hash": "c8653c8",
+    "date": "0223_0404"
+}

0223_0350_llava_one_vision_llava_qwen_lora_ov_32f_llava_onevision_model_args_8ff049/vsibench.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fff43618ca040c87d16704ddb173218533ccd63da8849b000b6a7d16e68ca17
+size 13437307

0223_0351_llava_one_vision_llava_qwen_lora_ov_32f_llava_onevision_model_args_1ad6e5/results.json

@@ -0,0 +1,112 @@
+{
+    "results": {
+        "vsibench": {
+            "alias": "vsibench",
+            "vsibench_score,none": 45.23785592237283,
+            "vsibench_score_stderr,none": "N/A"
+        }
+    },
+    "group_subtasks": {
+        "vsibench": []
+    },
+    "configs": {
+        "vsibench": {
+            "task": "vsibench",
+            "dataset_path": "nyu-visionx/VSI-Bench",
+            "dataset_kwargs": {
+                "token": true
+            },
+            "test_split": "test",
+            "full_docs": false,
+            "process_results_use_image": false,
+            "process_docs": "<function process_docs at 0x4002e1e830a0>",
+            "doc_to_visual": "<function vsibench_doc_to_visual at 0x4002e1e83760>",
+            "doc_to_text": "<function vsibench_doc_to_text at 0x4002e0b38040>",
+            "doc_to_target": "ground_truth",
+            "process_results": "<function vsibench_process_results at 0x4002e0b38c10>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "num_fewshot": 0,
+            "metric_list": [
+                {
+                    "metric": "vsibench_score",
+                    "aggregation": "<function vsibench_aggregate_results at 0x4002e0b39510>",
+                    "higher_is_better": true
+                }
+            ],
+            "output_type": "generate_until",
+            "generation_kwargs": {
+                "max_new_tokens": 16,
+                "temperature": 0.0,
+                "top_p": 1.0,
+                "num_beams": 1,
+                "do_sample": false,
+                "until": [
+                    "\n\n"
+                ]
+            },
+            "repeats": 1,
+            "should_decontaminate": false,
+            "metadata": [
+                {
+                    "version": 0.0
+                }
+            ],
+            "lmms_eval_specific_kwargs": {
+                "default": {
+                    "pre_prompt": "",
+                    "mca_post_prompt": "Answer with the option's letter from the given choices directly.",
+                    "na_post_prompt": "Please answer the question using a single word or phrase."
+                },
+                "gemini_api": {
+                    "pre_prompt": "",
+                    "mca_post_prompt": "Answer with the option's letter from the given choices directly.",
+                    "na_post_prompt": "Do not response anything other than a single number!"
+                },
+                "gpt4v": {
+                    "pre_prompt": "",
+                    "mca_post_prompt": "Answer with the option's letter from the given choices directly.",
+                    "na_post_prompt": "Do not response anything other than a single number!"
+                },
+                "pre_prompt": "",
+                "mca_post_prompt": "Answer with the option's letter from the given choices directly.",
+                "na_post_prompt": "Please answer the question using a single word or phrase."
+            }
+        }
+    },
+    "versions": {
+        "vsibench": "Yaml"
+    },
+    "n-shot": {
+        "vsibench": 0
+    },
+    "higher_is_better": {
+        "vsibench": {
+            "vsibench_score": true
+        }
+    },
+    "n-samples": {
+        "vsibench": {
+            "original": 5130,
+            "effective": 5130
+        }
+    },
+    "config": {
+        "model": "llava_onevision",
+        "model_args": "pretrained=/scratch/08367/zhiwen/work_dirs/llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-cut3r_only_stage2_lora_vsibench_02_23,attn_implementation=flash_attention_2,conv_template=qwen_1_5,model_name=llava_qwen_lora,max_frames_num=32,model_base=LLaVA-NeXT/checkpoints/LLaVA-Video-7B-Qwen2",
+        "batch_size": "1",
+        "batch_sizes": [],
+        "device": null,
+        "use_cache": null,
+        "limit": null,
+        "bootstrap_iters": 100000,
+        "gen_kwargs": "",
+        "random_seed": 0,
+        "numpy_seed": 1234,
+        "torch_seed": 1234,
+        "fewshot_seed": 1234
+    },
+    "git_hash": "c8653c8",
+    "date": "0223_0407"
+}

0223_0351_llava_one_vision_llava_qwen_lora_ov_32f_llava_onevision_model_args_1ad6e5/vsibench.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7783eef03dd4466f0fa5022d7ab9164fb06c9a81f778441a1559aa2878346700
+size 13456732

0223_2055_llava_one_vision_llava_qwen_lora_ov_32f_llava_onevision_model_args_2229cf/results.json

@@ -0,0 +1,112 @@
+{
+    "results": {
+        "vsibench": {
+            "alias": "vsibench",
+            "vsibench_score,none": 34.41087854228516,
+            "vsibench_score_stderr,none": "N/A"
+        }
+    },
+    "group_subtasks": {
+        "vsibench": []
+    },
+    "configs": {
+        "vsibench": {
+            "task": "vsibench",
+            "dataset_path": "nyu-visionx/VSI-Bench",
+            "dataset_kwargs": {
+                "token": true
+            },
+            "test_split": "test",
+            "full_docs": false,
+            "process_results_use_image": false,
+            "process_docs": "<function process_docs at 0x4002beb631c0>",
+            "doc_to_visual": "<function vsibench_doc_to_visual at 0x4002beb63880>",
+            "doc_to_text": "<function vsibench_doc_to_text at 0x4002bd50c160>",
+            "doc_to_target": "ground_truth",
+            "process_results": "<function vsibench_process_results at 0x4002bd50cd30>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "num_fewshot": 0,
+            "metric_list": [
+                {
+                    "metric": "vsibench_score",
+                    "aggregation": "<function vsibench_aggregate_results at 0x4002bd50d630>",
+                    "higher_is_better": true
+                }
+            ],
+            "output_type": "generate_until",
+            "generation_kwargs": {
+                "max_new_tokens": 16,
+                "temperature": 0.0,
+                "top_p": 1.0,
+                "num_beams": 1,
+                "do_sample": false,
+                "until": [
+                    "\n\n"
+                ]
+            },
+            "repeats": 1,
+            "should_decontaminate": false,
+            "metadata": [
+                {
+                    "version": 0.0
+                }
+            ],
+            "lmms_eval_specific_kwargs": {
+                "default": {
+                    "pre_prompt": "",
+                    "mca_post_prompt": "Answer with the option's letter from the given choices directly.",
+                    "na_post_prompt": "Please answer the question using a single word or phrase."
+                },
+                "gemini_api": {
+                    "pre_prompt": "",
+                    "mca_post_prompt": "Answer with the option's letter from the given choices directly.",
+                    "na_post_prompt": "Do not response anything other than a single number!"
+                },
+                "gpt4v": {
+                    "pre_prompt": "",
+                    "mca_post_prompt": "Answer with the option's letter from the given choices directly.",
+                    "na_post_prompt": "Do not response anything other than a single number!"
+                },
+                "pre_prompt": "",
+                "mca_post_prompt": "Answer with the option's letter from the given choices directly.",
+                "na_post_prompt": "Please answer the question using a single word or phrase."
+            }
+        }
+    },
+    "versions": {
+        "vsibench": "Yaml"
+    },
+    "n-shot": {
+        "vsibench": 0
+    },
+    "higher_is_better": {
+        "vsibench": {
+            "vsibench_score": true
+        }
+    },
+    "n-samples": {
+        "vsibench": {
+            "original": 5130,
+            "effective": 5130
+        }
+    },
+    "config": {
+        "model": "llava_onevision",
+        "model_args": "pretrained=/scratch/08367/zhiwen/work_dirs/llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-cut3r_stage2_lr1e-4_cat_02_23,attn_implementation=flash_attention_2,conv_template=qwen_1_5,model_name=llava_qwen_lora,max_frames_num=32,model_base=LLaVA-NeXT/checkpoints/LLaVA-Video-7B-Qwen2",
+        "batch_size": "1",
+        "batch_sizes": [],
+        "device": null,
+        "use_cache": null,
+        "limit": null,
+        "bootstrap_iters": 100000,
+        "gen_kwargs": "",
+        "random_seed": 0,
+        "numpy_seed": 1234,
+        "torch_seed": 1234,
+        "fewshot_seed": 1234
+    },
+    "git_hash": "c8653c8",
+    "date": "0223_2111"
+}

0223_2055_llava_one_vision_llava_qwen_lora_ov_32f_llava_onevision_model_args_2229cf/vsibench.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19dba4e52f22f327eb22ed1a3af41745fb701550c83d2676b77c9d0ea37a9990
+size 13364198

0223_2055_llava_one_vision_llava_qwen_lora_ov_32f_llava_onevision_model_args_3f39f5/results.json

@@ -0,0 +1,112 @@
+{
+    "results": {
+        "vsibench": {
+            "alias": "vsibench",
+            "vsibench_score,none": 54.84086609704796,
+            "vsibench_score_stderr,none": "N/A"
+        }
+    },
+    "group_subtasks": {
+        "vsibench": []
+    },
+    "configs": {
+        "vsibench": {
+            "task": "vsibench",
+            "dataset_path": "nyu-visionx/VSI-Bench",
+            "dataset_kwargs": {
+                "token": true
+            },
+            "test_split": "test",
+            "full_docs": false,
+            "process_results_use_image": false,
+            "process_docs": "<function process_docs at 0x4002b657caf0>",
+            "doc_to_visual": "<function vsibench_doc_to_visual at 0x4002b657d1b0>",
+            "doc_to_text": "<function vsibench_doc_to_text at 0x4002b657dcf0>",
+            "doc_to_target": "ground_truth",
+            "process_results": "<function vsibench_process_results at 0x4002b657e830>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "num_fewshot": 0,
+            "metric_list": [
+                {
+                    "metric": "vsibench_score",
+                    "aggregation": "<function vsibench_aggregate_results at 0x4002b657eb00>",
+                    "higher_is_better": true
+                }
+            ],
+            "output_type": "generate_until",
+            "generation_kwargs": {
+                "max_new_tokens": 16,
+                "temperature": 0.0,
+                "top_p": 1.0,
+                "num_beams": 1,
+                "do_sample": false,
+                "until": [
+                    "\n\n"
+                ]
+            },
+            "repeats": 1,
+            "should_decontaminate": false,
+            "metadata": [
+                {
+                    "version": 0.0
+                }
+            ],
+            "lmms_eval_specific_kwargs": {
+                "default": {
+                    "pre_prompt": "",
+                    "mca_post_prompt": "Answer with the option's letter from the given choices directly.",
+                    "na_post_prompt": "Please answer the question using a single word or phrase."
+                },
+                "gemini_api": {
+                    "pre_prompt": "",
+                    "mca_post_prompt": "Answer with the option's letter from the given choices directly.",
+                    "na_post_prompt": "Do not response anything other than a single number!"
+                },
+                "gpt4v": {
+                    "pre_prompt": "",
+                    "mca_post_prompt": "Answer with the option's letter from the given choices directly.",
+                    "na_post_prompt": "Do not response anything other than a single number!"
+                },
+                "pre_prompt": "",
+                "mca_post_prompt": "Answer with the option's letter from the given choices directly.",
+                "na_post_prompt": "Please answer the question using a single word or phrase."
+            }
+        }
+    },
+    "versions": {
+        "vsibench": "Yaml"
+    },
+    "n-shot": {
+        "vsibench": 0
+    },
+    "higher_is_better": {
+        "vsibench": {
+            "vsibench_score": true
+        }
+    },
+    "n-samples": {
+        "vsibench": {
+            "original": 5130,
+            "effective": 5130
+        }
+    },
+    "config": {
+        "model": "llava_onevision",
+        "model_args": "pretrained=/scratch/08367/zhiwen/work_dirs/llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-7B-Instruct-base_stage2_lr1e-4_cat_02_23,attn_implementation=flash_attention_2,conv_template=qwen_1_5,model_name=llava_qwen_lora,max_frames_num=32,model_base=LLaVA-NeXT/checkpoints/LLaVA-Video-7B-Qwen2",
+        "batch_size": "1",
+        "batch_sizes": [],
+        "device": null,
+        "use_cache": null,
+        "limit": null,
+        "bootstrap_iters": 100000,
+        "gen_kwargs": "",
+        "random_seed": 0,
+        "numpy_seed": 1234,
+        "torch_seed": 1234,
+        "fewshot_seed": 1234
+    },
+    "git_hash": "c8653c8",
+    "date": "0223_2108"
+}

0223_2055_llava_one_vision_llava_qwen_lora_ov_32f_llava_onevision_model_args_3f39f5/vsibench.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b916cc64a08eb74a4dd71ccb925632e0e2f4e21e1110e455074a2beb6b1f8490
+size 13363805