update

README.md

@@ -1,3 +1,11 @@
----
-license: apache-2.0
----
+# Open-Pandora Model Card
+
+## Model Status
+We currently hide the model weights due to data license issues. We will re-open the weights soon after we resolve this issue.
+
+## Model Details
+Open-Pandora is a faithful reproduction of the original [Pandora project](https://world-model.maitrix.org) developed by Maitrix. This model was trained on the Webvid dataset for 600,000 steps to simulate diverse world states by generating videos across various domains. It supports on-the-fly control using free-text actions.
+
+## Uses
+ For more information, please refer to [our GitHub repository](https://github.com/OpenSparseLLMs/Open-Pandora).
+ 

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<image>": 32000,
+  "[IMG_P]": 32001,
+  "<img_s>": 32002
+}

config.json

@@ -0,0 +1,88 @@
+{   
+    "video_model_name_or_path":"Chat-UniVi/Chat-UniVi",
+    "diffusion_model_name_or_path":"stabilityai/stable-diffusion-2-base",
+    "image_prefix_length": 64,
+    "use_diffusion_text_encoder": false,
+    "video_model_config": 
+    {
+        "_name_or_path": "",
+        "aarchitectures": "ChatUniViLlamaForCausalLM",
+        "architectures": [
+            "ChatUniViLlamaForCausalLM"
+        ],
+        "bos_token_id": 1,
+        "config": {
+            "spatial_cluster_rate0": 64,
+            "spatial_cluster_rate1": 32,
+            "spatial_cluster_rate2": 16,
+            "freeze": false,
+            "mm_tune": true,
+            "use_cluster": true,
+            "temporal_cluster_rate": 0.0625,
+            "vision_tune": false
+        },
+        "eos_token_id": 2,
+        "freeze_mm_mlp_adapter": false,
+        "hidden_act": "silu",
+        "hidden_size": 4096,
+        "image_aspect_ratio": "square",
+        "image_grid_pinpoints": null,
+        "initializer_range": 0.02,
+        "intermediate_size": 11008,
+        "max_position_embeddings": 4096,
+        "mm_hidden_size": 1024,
+        "mm_use_box_start_end": false,
+        "mm_use_im_patch_token": false,
+        "mm_use_im_start_end": false,
+        "mm_vision_select_feature": "patch",
+        "mm_vision_select_layer": -2,
+        "mm_vision_tower": "openai/clip-vit-large-patch14",
+        "model_type": "ChatUniVi",
+        "num_attention_heads": 32,
+        "num_hidden_layers": 32,
+        "num_key_value_heads": 32,
+        "pad_token_id": 0,
+        "pretraining_tp": 1,
+        "rms_norm_eps": 1e-05,
+        "rope_scaling": null,
+        "tie_word_embeddings": false,
+        "torch_dtype": "bfloat16",
+        "transformers_version": "4.31.0",
+        "tune_mm_mlp_adapter": false,
+        "use_cache": true,
+        "use_mm_proj": true,
+        "vocab_size": 32000
+    },
+    "use_image_prefix": true, 
+    "use_flash_attn": false,
+    "use_image_callbacks": false,
+    "rescale_betas_zero_snr": true,
+    "parameterization": "v",
+    "linear_start": 0.00085,
+    "linear_end": 0.012,
+    "num_timesteps_cond": 1,
+    "timesteps": 1000,
+    "first_stage_key": "video",
+    "cond_stage_key": "caption",
+    "cond_stage_trainable": false,
+    "conditioning_key": "hybrid",
+    "image_size": [
+        40,
+        64
+    ],
+    "channels": 4,
+    "scale_by_std": false,
+    "scale_factor": 0.18215,
+    "use_ema": false,
+    "uncond_type": "empty_seq",
+    "use_dynamic_rescale": true,
+    "base_scale": 0.7,
+    "fps_condition_type": "fps",
+    "perframe_ae": true,
+    "qformer_config":{
+        "model_name": "blip_2_qformer"
+    },
+    "diffusion_qformer_config":{
+        "hidden_size": 768
+    }
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.9,
+  "top_p": 0.6,
+  "transformers_version": "4.31.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23ce5743d89c57bfb1fac94fd5da6457fcd65a98f7d8c57fd01053ffff1276f5
+size 19518232066

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,67 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "[IMG_P]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<img_s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}