SimpleMemVLN FullContext dual-lane, no action history — base
epoch-1/ is a completed first-epoch snapshot at update 3852 of a
two-epoch, 7704-update schedule. Epoch 2 is still training and is not published here.
This is a mid-schedule snapshot, not an independently scheduled one-epoch model.
Initialized directly from the original Qwen3.5-4B base weights, with fresh step lanes.
Architecture and training
Qwen/Qwen3.5-4B revision 851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a.
FullContext attention with parallel step lanes at layers 16, 20, 24 and 28,
using the step_end clock. Four-way candidate logits from pretrained trainable
LM-head rows; no appended action-history tokens.
Serializer: vln_candidate_logits_no_action_history_v1.
Frozen vision encoder and merger, trainable language backbone and step lanes.
Complete trajectories, gradient checkpointing, CPU activation offload for long
sequences, BF16 and DeepSpeed ZeRO-2.
Joint R2R + English-guide RxR_15deg: 30,815 episodes (10,819 + 19,996). Global batch 8 = four H100 GPUs × one episode/rank × accumulation 2. Backbone/head LR 5e-6; step-lane LR 1e-4; warmup 232 updates; cosine decay to 10% of peak, weight decay 0.01, seed 429. Epoch-1 action-weighted training loss: 0.3897369707. These are training metrics; this snapshot has not been evaluated in Habitat.
Loading and provenance
Use SimpleMemVLN source commit fe9914d6c900b41f17df880753d651eb610d0837 and the pinned runtime documented
in the streaming_logits_dual branch. Download the epoch directory and use:
from qwen_vl.train.vln_runtime import load_checkpoint
model, serializer = load_checkpoint("downloaded_repo/epoch-1", pinned_base_model_path)
The navigation wrapper and step-lane weights are included in pytorch_model.bin.
This requires the SimpleMemVLN loader and the pinned base model/processor;
an unmodified AutoModel loader does not implement this navigation contract.
navigation.json records the complete recipe and architecture.
Model, tokenizer/processor, epoch report and selected provenance are published.
Optimizer/RNG tensors, dataset contents and credentials remain local.
SHA256SUMS.json records file hashes. Every uploaded file is downloaded from
the immutable publication commit and checked against its local SHA-256.