Add RAS-13B-General

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<mask_group_pred>": 32001,
+  "<mask_no>": 32003,
+  "<mask_pool_pred>": 32000,
+  "<mask_yes>": 32002
+}

config.json

@@ -0,0 +1,92 @@
+{
+  "_name_or_path": "/mnt/localssd/save/llava-v1.5-13b-0730-llavapt-ptv2-directbinarymask",
+  "architectures": [
+    "SmartSegLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "exclusive_mask_decoding": true,
+  "freeze_mask_classifier": false,
+  "freeze_mask_projector": false,
+  "freeze_mask_reprojector": false,
+  "freeze_vision_projector": false,
+  "freeze_vision_tower": true,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "image_aspect_ratio": "pad",
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "mask_decoding_binary_threshold": 0.5,
+  "mask_loss_binary": false,
+  "mask_loss_binary_pos_weight": 5.0,
+  "mask_loss_direct_binary": true,
+  "mask_loss_set_pred": true,
+  "mask_loss_type": "mse+infonce",
+  "mask_projector_input_features": [
+    "clip_-2",
+    "siglip",
+    "open_clip",
+    "dinov2",
+    "sincos_pe"
+  ],
+  "mask_projector_type": "mlp2x_gelu",
+  "mask_reprojector_type": "mlp2x_gelu",
+  "max_length": 4096,
+  "max_position_embeddings": 4096,
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "model_type": "smart_seg_llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretrain_projectors": false,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "version": "v1",
+  "vision_backbone_resolutions": [
+    336,
+    378,
+    1024,
+    518,
+    448
+  ],
+  "vision_backbones": [
+    "openai/clip-vit-large-patch14-336",
+    "google/siglip-so400m-patch14-384",
+    "convnext_xxlarge",
+    "facebook/dinov2-large",
+    "sincos_pe"
+  ],
+  "vision_hidden_size": [
+    1024,
+    1152,
+    3072,
+    1024,
+    1024
+  ],
+  "vision_output_features": [
+    "clip_-2",
+    "siglip",
+    "open_clip",
+    "dinov2",
+    "sincos_pe"
+  ],
+  "vision_pe_hidden_size": 1024,
+  "vision_pe_patches_per_side": 32,
+  "vision_pe_scale": 1.0,
+  "vision_processor": "openai/clip-vit-large-patch14-336",
+  "vision_projector_input_features": [
+    "clip_-2"
+  ],
+  "vision_projector_type": "mlp2x_gelu",
+  "vocab_size": 32004
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "transformers_version": "4.37.2"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1f7150e71868da3d7b053a1c1d473b6da0da715fad77a0729c4f11da5753b6c
+size 4978306760

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:114c2513f19c41423c8a0af057a874166d3b449e3f014604b389e3f785b7d285
+size 4970422232

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45dac3a159ab075002353770bfd94f8e4f241e56733100455108dd45f0f74de7
+size 4970422256

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dba3e0228538b6403292198b1ffbd0971752e43b1273fbe8637ef64babc8d348
+size 4933701504

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86f83c642f32fa6c5749f9677658a6b6fdd7b953b8783d2ed2243b893102674c
+size 4933722216

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9100e2959fe653665de254cc3fe51df7c6cae80308587086040810a462a07121
+size 4973874000

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cca538d377ac3e4fda83c55d6a0568310a52b9fc59ddf10e1f96c45a482223e0
+size 380170778

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "<unk>",
+  "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 +1,74 @@
+{
+  "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": "<mask_pool_pred>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<mask_group_pred>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<mask_yes>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<mask_no>",
+      "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
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a19e47e7dfebe7862f83cba85ccc45ede2fd3c5fa51df714cc00b57e799e8c31
+size 6328