Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ 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
+checkpoint-1900/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-1900/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|point_end|>": 151653,
+  "<|point_pad|>": 151654,
+  "<|point_start|>": 151652,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656
+}

checkpoint-1900/config.json

@@ -0,0 +1,139 @@
+{
+  "_name_or_path": "manycore-research/SpatialLM1.1-Qwen-0.5B",
+  "architectures": [
+    "SpatialLMQwenForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "chorus_aligned_root": "/work/luka_milivojevic/3rscan_subset_chorus_sonata_native_cache_rio10_crop_radius_m0p25",
+  "chorus_checkpoint": "/work/GaussianWorld/huggingface/models--SceneSplatPro--chorus/snapshots/6a330d00c094c0746d19f9871d2a17647ad5986f/lang-dino-enc-pretrain-scan-ppv2-mp3d-mcmc.pth",
+  "chorus_config": "chorus_3dgs",
+  "chorus_contrastive_backprop_sonata": false,
+  "chorus_contrastive_cosine_weight": 1.0,
+  "chorus_contrastive_decay_start_ratio": 1.0,
+  "chorus_contrastive_exact_only": false,
+  "chorus_contrastive_info_nce_weight": 0.1,
+  "chorus_contrastive_loss_current_weight": 1.0,
+  "chorus_contrastive_loss_final_weight": 1.0,
+  "chorus_contrastive_loss_weight": 1.0,
+  "chorus_contrastive_min_matched_tokens": 32,
+  "chorus_contrastive_mse_weight": 0.25,
+  "chorus_contrastive_temperature": 0.07,
+  "chorus_contrastive_warmup_ratio": 0.0,
+  "chorus_disable_drop_path": true,
+  "chorus_discard_unmatched_tokens": false,
+  "chorus_drop_pcd_probability": 0.6,
+  "chorus_exact_match_first": true,
+  "chorus_fourier_head_layer_norm": false,
+  "chorus_fusion_chorus_weight": 0.5,
+  "chorus_fusion_enabled": true,
+  "chorus_fusion_gate_hidden_dim": 256,
+  "chorus_fusion_gate_mode": "global",
+  "chorus_fusion_mode": "chorus_coord_matched",
+  "chorus_fusion_transformer_dropout": 0.0,
+  "chorus_fusion_transformer_ffn_dim": 1024,
+  "chorus_fusion_transformer_heads": 8,
+  "chorus_fusion_transformer_layers": 2,
+  "chorus_init_fourier_head_from_sonata": true,
+  "chorus_input_mode": "prepared",
+  "chorus_match_grid_radius": 1,
+  "chorus_min_valid_label_fraction": 0.3,
+  "chorus_mirror_sonata_trainability": true,
+  "chorus_missing_policy": "pcd",
+  "chorus_modality_dropout_rate": 0.5,
+  "chorus_native_match_radius": 2,
+  "chorus_repo_root": "/home/luka_milivojevic/SceneSplatPro",
+  "chorus_share_fourier_head_with_sonata": false,
+  "chorus_trainable_name_patterns": "backbone",
+  "chorus_use_sonata_lattice_for_coord_matched": true,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "image_feature_dim": 768,
+  "image_input_mode": "none",
+  "image_projector": "mlp",
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "modality_dropout_rate": 0.0,
+  "model_type": "spatiallm_qwen",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "obj_token": "<OBJ>",
+  "obj_token_id": null,
+  "object_feature_dim": 768,
+  "object_feature_loss_weight": 1.0,
+  "point_backbone": "sonata",
+  "point_config": {
+    "enc_channels": [
+      48,
+      96,
+      192,
+      384,
+      512
+    ],
+    "enc_depths": [
+      3,
+      3,
+      3,
+      12,
+      3
+    ],
+    "enc_mode": true,
+    "enc_num_head": [
+      3,
+      6,
+      12,
+      24,
+      32
+    ],
+    "enc_patch_size": [
+      1024,
+      1024,
+      1024,
+      1024,
+      1024
+    ],
+    "in_channels": 6,
+    "mask_token": true,
+    "mlp_ratio": 4,
+    "num_bins": 1280,
+    "order": [
+      "z",
+      "z-trans",
+      "hilbert",
+      "hilbert-trans"
+    ],
+    "stride": [
+      2,
+      2,
+      2,
+      2
+    ]
+  },
+  "point_end_token_id": 151653,
+  "point_start_token_id": 151652,
+  "point_token_id": 151654,
+  "projector": "mlp",
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.1",
+  "use_2d_tokens": false,
+  "use_3d_tokens": true,
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vision_attn_implementation": "eager",
+  "vision_global_token": "cls_plus_patch_mean",
+  "vision_gradient_checkpointing": false,
+  "vision_pool_grid_size": 4,
+  "vision_tower_name_or_path": "facebook/dinov2-base",
+  "vision_train_last_n_blocks": 2,
+  "vision_train_mode": "last_blocks",
+  "vocab_size": 151936
+}

checkpoint-1900/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "transformers_version": "4.46.1"
+}

checkpoint-1900/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56c92944ac50f8b5456b5508b4a34a3517dd6559e88a701f6781759e84fa2adb
+size 2946725292

checkpoint-1900/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5db4a7ff0c74025b450eb34c2dfb6fe67d80a51b64289f22734b9a8b6a02e93a
+size 5699156684

checkpoint-1900/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e05b506a5d70051cd596fd15eca20f6033f4f7df0408732af9353c02cb1adbd6
+size 14244

checkpoint-1900/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c60d0e90bb8eb965e550c72c3c5e2d6f824f97e3e168e363db414434d82e5005
+size 1064

checkpoint-1900/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|point_start|>",
+    "<|point_end|>",
+    "<|point_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1900/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a993952f62bf1f44eac28586835f4a298d7414dc8ecc3ec7e0ef3d51294161d
+size 11421893

checkpoint-1900/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|point_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|point_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|point_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|point_start|>",
+    "<|point_end|>",
+    "<|point_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1900/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08bc588b9fa8bbdcab61726a25b6ebe6f9f720d09151f2457c20cef2b1b23bd4
+size 5560