Publish joint R2R + RxR_15deg FullContext+B epoch 1 (step 3852)

.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
+epoch-1/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,48 @@
+---
+base_model: Qwen/Qwen3.5-4B
+library_name: transformers
+tags:
+- vision-language-navigation
+- r2r
+- rxr
+- simplememvln
+- intermediate-checkpoint
+---
+# SimpleMemVLN joint R2R + RxR_15deg FullContext+B
+
+**Not yet evaluated in Habitat.** Training loss is not a navigation success metric.
+
+## Published snapshot
+`epoch-1/` contains the completed first epoch, optimizer update 3852.
+This is a **mid-schedule snapshot of one two-epoch cosine run**, not an
+independently scheduled one-epoch model. The second epoch is not part of this
+publication. Training continues separately; uploading does not change training.
+
+## Recipe and provenance
+Joint R2R training data and English-guide RxR_15deg trajectories, full episodes.
+Initialized from Qwen/Qwen3.5-4B revision
+`851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a`.
+Source base commit: `6bb2b10a2fe21cb6e25a265afc5a2af39b7de4f6`, with input-staging
+and checkpoint-recovery patches. The tested source is identified by
+`source.sha256`; the dataset manifest by `manifest.sha256`.
+Serializer: `vln_append_only_chat_v1`. Native LLM text-action head (option B),
+gold action history; per-action mean token cross-entropy including assistant
+terminator, normalized over actions in the distributed accumulation window.
+Frozen vision/merger, trainable text backbone and LLM head; BF16, ZeRO-2,
+nonreentrant gradient checkpointing with long-sequence activation offload.
+Full-context causal attention, no trajectory truncation or TBPTT.
+Global batch 8 = four H100 GPUs × one episode/rank × GAS2.
+Two epochs, 7704 optimization updates, 232 warmup updates, peak LR 5e-6,
+cosine decay to 10% of peak, weight decay 0.01, seed 429.
+Observation-before-action alignment is declared but not independently
+verified against collector source or Habitat replay.
+
+## Loading and integrity
+Use the SimpleMemVLN wrapper loader
+`qwen_vl.train.vln_runtime.load_checkpoint(epoch_directory, base_model_path)`
+with the pinned base snapshot. These are navigation-wrapper weights, not a
+plain AutoModel state dictionary. Navigation metadata records the recipe.
+Only model, processor, tokenizer, provenance and selected training metadata
+are published. Optimizer/RNG state, dataset images and credentials stay local.
+`SHA256SUMS.json` records content hashes. The uploader downloads every file
+at its immutable Hub commit and verifies SHA256 before reporting success.

SHA256SUMS.json

@@ -0,0 +1,14 @@
+{
+  "README.md": "7773178322d52c20ef11c7ef8e9e2fb6e432e6985035bd0a6e33de26fe16e20e",
+  "epoch-1/chat_template.jinja": "a4aee8afcf2e0711942cf848899be66016f8d14a889ff9ede07bca099c28f715",
+  "epoch-1/config.json": "2451a8786918f4c348acb32c438d9a127098c022334ae1a7713ce5be588a7df1",
+  "epoch-1/navigation.json": "d1d16f2c26e926268e05baa459454c46172a5ccc42271185e5dd106ba25c26b9",
+  "epoch-1/processor_config.json": "d89ef49ce9cd37fbf510158e13c1ef063d9286411c1ec9049932dbe0487143b1",
+  "epoch-1/pytorch_model.bin": "53404dfc02b46063b54422954b7cb8635c7ff893a4c6f44aeec70bb7693d737f",
+  "epoch-1/tokenizer.json": "06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523",
+  "epoch-1/tokenizer_config.json": "7488550a894dcf741616126e322ea31d66cf9457b59ec5825f4c7efdced421f8",
+  "epoch-1/trainer_state.json": "91aa485b14f33e9af7539a557255bf99e5b9355ccb00ba2dcd0b42cbc980b8ee",
+  "manifest.sha256": "b679ab7ddb7e1a7af197d1598ac2253edb3624644136504d4f25ae575db8212f",
+  "reports/epoch-1.json": "db680518d95702f0a91310e481c4cd53bdcea66db8dfa3b78ae7edf9b11e57b8",
+  "source.sha256": "8c0410277f430ebb4d460dcc597dc5433a2dcce6156b81bc2d13495165ac715a"
+}

epoch-1/chat_template.jinja

@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

epoch-1/config.json

@@ -0,0 +1,112 @@
+{
+  "architectures": [
+    "Qwen3_5ForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "eos_token_id": 248046,
+  "image_token_id": 248056,
+  "model_type": "qwen3_5",
+  "pad_token_id": 248044,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_output_gate": true,
+    "bos_token_id": null,
+    "dtype": "bfloat16",
+    "eos_token_id": 248044,
+    "full_attention_interval": 4,
+    "head_dim": 256,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 9216,
+    "layer_types": [
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention"
+    ],
+    "linear_conv_kernel_dim": 4,
+    "linear_key_head_dim": 128,
+    "linear_num_key_heads": 16,
+    "linear_num_value_heads": 32,
+    "linear_value_head_dim": 128,
+    "mamba_ssm_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "mlp_only_layers": [],
+    "model_type": "qwen3_5_text",
+    "mtp_num_hidden_layers": 1,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 4,
+    "pad_token_id": null,
+    "partial_rotary_factor": 0.25,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        11,
+        11,
+        10
+      ],
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 10000000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 248320
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.11.0",
+  "use_cache": false,
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 24,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "qwen3_5_vision",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2560,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053
+}

epoch-1/navigation.json

@@ -0,0 +1,106 @@
+{
+  "serializer": "vln_append_only_chat_v1",
+  "template_sha256": "fb79cf3922f74475e9a5faaac8c08d2f79a3ca7bef5dbf434f3f7726119229b8",
+  "actions": [
+    "MOVE_FORWARD",
+    "TURN_LEFT",
+    "TURN_RIGHT",
+    "STOP"
+  ],
+  "habitat_ids": [
+    1,
+    2,
+    3,
+    0
+  ],
+  "action_token_ids": [
+    [
+      28164,
+      61846,
+      248046
+    ],
+    [
+      15834,
+      18440,
+      248046
+    ],
+    [
+      15834,
+      20549,
+      248046
+    ],
+    [
+      48964,
+      248046
+    ]
+  ],
+  "eos": 248046,
+  "separator_ids": [
+    198
+  ],
+  "rgb_shape": [
+    480,
+    640,
+    3
+  ],
+  "position_convention": "logical_text_plus_native_mrope_v1",
+  "rotary_precision": "fp32_preserved_across_module_casts_v1",
+  "config": {
+    "model": {
+      "backbone": "Qwen/Qwen3.5-4B",
+      "revision": "851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a",
+      "output_mode": "qwen_text"
+    },
+    "observations": {
+      "expected_rgb_shape": [
+        480,
+        640,
+        3
+      ],
+      "expected_visual_tokens": 300,
+      "max_prefix_tokens": 2048,
+      "serializer_version": "vln_append_only_chat_v1",
+      "max_step_group_tokens": 384,
+      "append_action_tokens": true
+    },
+    "memory": {
+      "mode": "full_context",
+      "kv_window_steps_including_current": null,
+      "evict_before_new_step": false,
+      "kv_guard_tokens": 262144
+    },
+    "training": {
+      "use_cache": false,
+      "microbatch_episodes_per_rank": 1,
+      "nominal_episodes_per_update": 8,
+      "gradient_accumulation_steps": 2,
+      "model_max_length": 262144,
+      "epochs": 2,
+      "backbone_lr": 5e-06,
+      "classifier_lr": 5e-06,
+      "weight_decay": 0.01,
+      "warmup_steps": 232,
+      "seed": 429,
+      "checkpoint_decoder_layers": true,
+      "length_bucket_pool_episodes": 64,
+      "tail_policy": "accelerate_repeat",
+      "activation_offload_min_tokens": 65536,
+      "supervise_assistant_terminator": true,
+      "expected_total_steps": 7704,
+      "expected_warmup_steps": 232,
+      "dataloader_num_workers": 4,
+      "save_strategy": "epoch",
+      "save_total_limit": null
+    },
+    "runtime": {
+      "text_attention": "flash_attention_2",
+      "vision_attention": "flash_attention_2",
+      "vision_microbatch_images": 4,
+      "max_logical_context_tokens": 262144
+    },
+    "generation": {
+      "max_response_tokens_including_eos": 16,
+      "fixed_separator": "\n"
+    }
+  }
+}

epoch-1/processor_config.json

@@ -0,0 +1,60 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

epoch-1/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53404dfc02b46063b54422954b7cb8635c7ff893a4c6f44aeec70bb7693d737f
+size 10350179723

epoch-1/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325

epoch-1/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "local_files_only": true,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

manifest.sha256

@@ -0,0 +1 @@
+5deb425d2594ce96931dd6ce12bd6084b066cd44f04808c1dd3ee2e4b3672933  /mnt/data/vmo-ai-task/anhdh35/SimpleMemVLN/artifacts/r2r_rxr15_train_20260929.jsonl

source.sha256

@@ -0,0 +1,78 @@
+1335aae0e90c8cee5e467270e283c7f59bfcc0d4f3988febffc53ee3707abfec  configs/r2r_uniform8.json
+8f51ed28c48d7edd89314771baa6454535d275ae786e92aa1c1bc40582fb4b6b  configs/vln_joint_b_2epoch_bs8.yaml
+05a2f9be2f36e9352bc8014961ed2a433fcac0a98eda4f6bf48a0e8edd4d43b4  configs/vln_memory_window8.yaml
+ceb1cfa33701cba9a313a9c06c7edb45871ff73733dea18050c8c3f328275809  configs/vln_r2r_b_3epoch_bs8.yaml
+50a06a8d1944d8604497db1c0a15139618b67c2467382bdd952cae6bcf7389a0  configs/vln_r2r_v0_base.yaml
+bef4a0e7bf4b38059c0cb34167f0ec29d9debbd9b76ba05532d2e83b954abc49  configs/vln_r2r_v0_classification.yaml
+b19612c035a1640691f94a9d3b3118ce4324b2c23d72baac26d7ceda8560b262  configs/vln_r2r_v0_qwen_text.yaml
+ea79511c0cb47627c1e7365d68f39d58794763a99d42c883daa0c5c1027e8572  scripts/__init__.py
+feb26015dad55132cf28feb600e469fb9ee43b93d688f5fb2ef1b2d117ef8ab0  scripts/vln/__init__.py
+7a7e0b1f38188683dd5862975430c6b22aba9a1b535a29353d2390986254a1fc  scripts/vln/audit_data.py
+30227974994c37ac1998cd494968411751aa3a9333e14468cc8b181e4018f3a4  scripts/vln/campaign_preflight.py
+d928ead9cf1bdda95ccb3ad7a8ee4ac2c97b2f3601cb5151d39131d20f849846  scripts/vln/check_compat.py
+4bc0fe0f536b0789b47313950c0b9cabae8686f4b4378f3b85c3b4c83310cccc  scripts/vln/check_distributed_loss.py
+54d1699a4a0da81f47a156f2e01792e25566177bd2babdb19e09e3a300f10b7d  scripts/vln/check_distributed_resume.py
+43de9fabc119b3ae3216f9987016d4375a939740af4840ac84e7044b4fca7d34  scripts/vln/check_epoch_saving.py
+54ac07b888ae22756586f1517d321e315e10e8feff47d1996ebe6562f46032db  scripts/vln/check_generated_history.py
+ac81b82ca9c91248cee8b1952c3d3242e33ce63f096c2fd15b800024df741978  scripts/vln/check_gradients.py
+1c0d58c4af450f8f5f9739472e5f82de0c89eaa5f1c12ec338f3009ab109c43b  scripts/vln/check_model_process.py
+7910578a13073ca41221cfb02db5e1e3a1aabe3929e97575acca8a81fa2b5228  scripts/vln/check_parity.py
+4414dfef07114db7a0ae83ef5e137991aa1c8122f5ec04c5a6e4837c28b0b3fc  scripts/vln/check_real_gdn.py
+74016ef65f6a92dd8303080fd917165df911517c5979eeab8f7b1a00ecbb7cea  scripts/vln/check_recovery_saving.py
+a624c808939867505184af8edbfa49302411befb60e269ae5ceaf9f65c121258  scripts/vln/check_reload.py
+88c64aeed1e523671d75917fab12a10125e4583ee49cd24277dcf784ae3152f9  scripts/vln/fingerprint.py
+c6d3b77dae038d88a977ef1e54fdd3da227863532c7eb642c0d7f6a8f8aadb2a  scripts/vln/prepare_joint.py
+c1ea6588ff4d141f5ee6e2cbc4e8b60f79fa5feeb72420083b53d70eb9fdbdce  scripts/vln/prepare_r2r.py
+bb9836ab32f37cfab6fc121872caf3dd7b11eb1981586adfdce3296b8f523660  scripts/vln/profile_episode.py
+9fc81dbaa2305e018b8928fbee9a7bea0528a262effdd40746ee616254b0154e  scripts/vln/profile_input_staging.py
+c2062775688948b15b9e3121928be31a9b682abed0fbfbe347dbece5f7f6a851  scripts/vln/profile_stream.py
+f328ef197cb7a9be8868658b965222a8d1dd863ffb64e36e46ff34322247cd0b  scripts/vln/report_campaign.py
+72a63ee59d5f7cc848c34a2f0ec8c263a2c58ad7f7d8c57b1c822fc7e757a667  scripts/vln/submit_campaign.py
+912bc7296db97690312f6e2f3feb0c2588e6a5d17e3ad46b985f5a24752abd0d  scripts/vln/summarize_run.py
+c5abab2738bbd0f5d726f4f99354b14f937807aaa2d5046e82b9af4f790e2b9f  scripts/vln/upload_campaign.py
+e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855  src/qwen_vl/__init__.py
+001861a6bb7633870139fd217123a0645a321509b0f334a1d5b9b90cbfd121ff  src/qwen_vl/contracts.py
+bde5ddc22a4a6bdd770ad2f33654de2f132c817b2a0cfe25779a6c597d2a433f  src/qwen_vl/data/__init__.py
+69049e220bdbf6f5f6e495a6d36c85c024af3b7792d8f9b5b4d5f905ed15bbd1  src/qwen_vl/data/data_qwen.py
+8320ae7d1f8f38de60674e467e702c2ce505f7f6cc42a039c81a391e87738074  src/qwen_vl/data/episode_dataset.py
+b31801ff0f01ecf0e22ec18dcb270af2fe4a33483512542696e7f3550bc49ffd  src/qwen_vl/data/episode_serializer.py
+cd0716138ae19d0b83d24c7c7812b767937769730a68e8b38cfe1c888cc3e9b0  src/qwen_vl/eval/__init__.py
+653635a4f4a24cfb9fc4e179968c879f7b0cb2a2a3ee4128dad5e46debb9025f  src/qwen_vl/eval/habitat_r2r.py
+1afc3ac43cfaf76f6038249107d7f9c7d0b8bedc0fa5da3a77a5475d2f19f130  src/qwen_vl/eval/metrics.py
+91a67bfc89269b248fd117c1bee2e89bf4508419c52bfb36a5802ec795d05e78  src/qwen_vl/models/__init__.py
+f815b55243dcc25037ac36a33caf1961e903b801cbcd97b9c3e99c98d335ca0e  src/qwen_vl/models/activation_offload.py
+94086a0ad9afdbb1354a7847f099e1a70f25989a1999937998d2048f4d967233  src/qwen_vl/models/nav_model.py
+f2fc60a24705fd98f663ad59abb8ed980150771a1e74f91ed3ad16d86cf7d1ec  src/qwen_vl/stream/__init__.py
+9fd3cf471f115024ae695cea534fdeafa1e58a36be8a567abb5f4984e3ccbc18  src/qwen_vl/stream/cache.py
+9e9b397cd3abdfd0aa7d42646f1aa817ac8c58027827c9773cfbf46bb1774279  src/qwen_vl/stream/positions.py
+2709ffab5a12bd7dd67ee8123a4620b381417ae120691385649f6d6c40208eb0  src/qwen_vl/stream/server.py
+09ba03c024944cb9af2061ea07755c195a042b5087340f6dd2601ab523ad042a  src/qwen_vl/stream/session.py
+1ce29f74887712443ade30e8b1e7e20df0c33a1612d39e726217b681b2de0c6a  src/qwen_vl/stream/window_attention.py
+1cd337494566de239c80d95aefdcac1996a5cc1a787a266ccea8a4d0259a9822  src/qwen_vl/train/argument.py
+aa2f772ceaffcb9dc09ca3a0dd7ae878c082337b7270dc4c27f9ec71a020d591  src/qwen_vl/train/campaign.py
+b8af85b47bdb3bbf73f1c9e294fc8ddc0cdad40b7723bd0afd3e66000dd44b4e  src/qwen_vl/train/recovery.py
+63ae756ee57b429bcb48f2ab5f2d97f8685fa4a29d8288df78babca73a884dc5  src/qwen_vl/train/sampler.py
+9f3e81b29161d9e1c9b4c7c210dd1bcfa96506972a08535e7bbade2be7b912a0  src/qwen_vl/train/train_episode.py
+799a41a03b929dc73bed9fe8fc9e899854a20e5901b608876d706467536fdb49  src/qwen_vl/train/train_qwen.py
+ac4ed753419e26f2315ab61753f5bd68c5f8ae39a7d22672d121ecf434b40a36  src/qwen_vl/train/trainer.py
+c2ab553943b035aa99cdfcfa66e00b54581876c5e5a18d422af226e08dc5e7c9  src/qwen_vl/train/vln_runtime.py
+68ebdb7b97cdb29aa993117285541ee31f7105161b2d5c6b1e90e05cb3c48203  tests/vln/test_activation_offload.py
+6fb5652db21a50016db4410c8b049edd29a04d4f726c7c3af921c85031b3b8a2  tests/vln/test_campaign.py
+1176932208ffda58c953c3c37d987a5b2b1b90bdbb7eb8dce9eb36bc3377b436  tests/vln/test_campaign_reporting.py
+12c3c959ffe3ce63d4f9636a701d2f513d54f7a76aa3d93b647ebeb749dbd42a  tests/vln/test_contracts.py
+34402c86919445cdde9b07354947cee46aadce255ac281bace26ac2df0591aa2  tests/vln/test_eval_metrics.py
+55e8117b448f087e6d7f022d44d854a3ad9a85945161071e1f14477052b184ca  tests/vln/test_joint_manifest.py
+14fed6b79c34bc579a295dc87e4cf0fe86a6793c67bb3e7a8b8779df979213e1  tests/vln/test_native_reference.py
+8b5ff08d993c2651cd92992cbe5f0857a1c2a79fd7840a596b3cd741fc4ab227  tests/vln/test_publication.py
+ac8512e331784dd41990a9f03bca78fcb3acb2faad49bcc0c0e8289cd422b1cf  tests/vln/test_recovery.py
+bc02c88519a22cb3101097b535c6735fc7b9a3cafb2dfc5658bcc8747cb0f129  tests/vln/test_serializer.py
+3031966cde5eb220f5c0f9163d1b6acfb876a7728f08306145efce4110083561  tests/vln/test_session.py
+d62d30e17d06228fa96b7429bac6d31c1142a7a915f31a68b150605f1ba759ba  tests/vln/test_stream_core.py
+363f85f5cff9e060daa5f48664787fbd49afafda312a4a0226b0721b42b720bd  tests/vln/test_submission.py
+d42822baab48a696cc1644e0bddd06cdc123fb2aa98be04066f2c48c766caaf6  tests/vln/test_training.py
+cf210c5aab7bf8058903427273d36de6bb9e2128f511710fc2a47e3f385d5b5f  train/slurm/joint_b.slurm
+7cfc0613f36cf3668ddac192053dd6f1ae471a9cd84c78de6c83a5f4a89d619b  train/slurm/preflight_b.slurm
+e9b802862a218424f67e819c485504880c0b9e06a15baa65fdb907ad0776f178  train/slurm/run_b.sh
+f586cc1cbb37bcbe5afdc9bd644764a7e689796993577b9f5ba8cc0f7c4fd558  train/slurm/run_joint_b.sh
+f315aeec69b43a091a139709228a9f4d6e8d346d7b2d72845fe2e0944513e824  train/slurm/train_b.slurm
+16a3932e32eedc2b5c77eb16cb0cbbd14f3afc42a5f67d3730d72935d3540cf7  train/slurm/upload_b.slurm