upload model

added_tokens.json

@@ -0,0 +1,14 @@
+{
+  "</s>": 2,
+  "<im_end>": 32002,
+  "<im_patch>": 32000,
+  "<im_start>": 32001,
+  "<s>": 1,
+  "<so_end>": 32008,
+  "<so_patch>": 32006,
+  "<so_start>": 32007,
+  "<unk>": 0,
+  "<vi_end>": 32005,
+  "<vi_patch>": 32003,
+  "<vi_start>": 32004
+}

config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "GroundingGPT-7B",
+  "architectures": [
+    "LEGOLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_aspect_ratio": "pad",
+  "image_grid_pinpoints": null,
+  "image_token_len": 576,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_frame": 64,
+  "max_position_embeddings": 4096,
+  "mm_use_im_patch_token": true,
+  "mm_use_im_start_end": true,
+  "mm_vision_hidden_size": 1024,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "openai/clip-vit-large-patch14-336",
+  "model_type": "LEGO",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "num_query_token": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "sound_end_token": 32008,
+  "sound_patch_token": 32006,
+  "sound_start_token": 32007,
+  "sound_token_len": 8,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.0",
+  "tune_mm_mlp_adapter": false,
+  "use_cache": true,
+  "use_mm_vision_proj": true,
+  "video_end_token": 32005,
+  "video_patch_token": 32003,
+  "video_start_token": 32004,
+  "video_token_len": 64,
+  "vocab_size": 32009
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.34.0",
+  "use_cache": false
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca405ca6eebc01b32ba66e29fe000bccb38752e8ba7cbda00fc671bce203664a
+size 9976854515

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30d3c50f2245363622105d30c56a4841cb33505ab0111b6da100292e1a0ce435
+size 8216712443

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>",
+    "<im_patch>",
+    "<im_start>",
+    "<im_end>",
+    "<vi_patch>",
+    "<vi_start>",
+    "<vi_end>",
+    "<so_patch>",
+    "<so_start>",
+    "<so_end>"
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<unk>",
+  "unk_token": "<unk>"
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,129 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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": "<im_patch>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<im_start>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<im_end>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<vi_patch>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<vi_start>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<vi_end>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<so_patch>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<so_start>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<so_end>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>",
+    "<im_patch>",
+    "<im_start>",
+    "<im_end>",
+    "<vi_patch>",
+    "<vi_start>",
+    "<vi_end>",
+    "<so_patch>",
+    "<so_start>",
+    "<so_end>"
+  ],
+  "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",
+  "tokenizer_file": null,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5fedfe69a7014dd05bc595ff805c9b3c9ca5ad087acfc56849d9b0eee156909
+size 5627