They count different things, and the card contradicts itself. The Nature paper's methods say the 1.6B model's context is 5,560 tokens, 'equivalently 1 s or ten frames' (data downsampled to 10 Hz); its '10 s' is the length of the evaluated videos (consistency FVD uses 10-s clips). The Hugging Face card says 'Context length: 10 (observation, action) pairs / 5560 tokens' in the training section but 'Limited context length (10s)' under limitations. Ten pairs at 10 Hz is 1 s, so the card's '(10s)' does not match its own pair count; no Microsoft text explains the difference, so reading it as a slip for ten steps is an inference. Code defaults agree with ten frames: run_dreaming.py sets context_length 10.
They count different things, and the card contradicts itself. The Nature paper's methods say the 1.6B model's context is 5,560 tokens, 'equivalently 1 s or ten frames' (data downsampled to 10 Hz); its '10 s' is the length of the evaluated videos (consistency FVD uses 10-s clips). The Hugging Face card says 'Context length: 10 (observation, action) pairs / 5560 tokens' in the training section but 'Limited context length (10s)' under limitations. Ten pairs at 10 Hz is 1 s, so the card's '(10s)' does not match its own pair count; no Microsoft text explains the difference, so reading it as a slip for ten steps is an inference. Code defaults agree with ten frames: run_dreaming.py sets context_length 10.
Curator qualifications: Nature Methods: '1.6B WHAM: the context length is 5,560 tokens, or equivalently 1 s or ten frames' and '894M WHAM: the context length is 2,720 tokens, or equivalently 1 s or ten frames'; 'After downsampling to 10 Hz'; 'we make the following publicly available: trained models (two WHAM sizes), the WHAM Demonstrator and a sample evaluation dataset'. Card line 183 'Context length: 10 (observation, action) pairs / 5560 tokens'; line 204 'Limited context length (10s)'. LICENSE.md: use 'solely for non-commercial, non-revenue generating, research purposes'; 'c) Models ... you may use the model(s), but you may not distribute the models'; 'e) Share, publish, distribute or lend the Materials ... provide the Materials as a stand-alone hosted solution ... or transfer'. Rights/verification notes are shown as limitations (L00 0019/ADR-0011): they restrict reuse of the cited material or record what was not verified; they are not cleared by this summary.
Limitations: [rights_conflict_record] eligible_conflicts_preserved
Evidence status: statements located in the cited sources by a correlated desk review (Claude); not executed; not independently reviewed.
[sourced_fact] They count different things, and the card contradicts itself. The Nature paper's methods say the 1.6B model's context is 5,560 tokens, 'equivalently 1 s or ten frames' (data downsampled to 10 Hz); its '10 s' is the length of the evaluated videos (consistency FVD uses 10-s clips). The Hugging Face card says 'Context length: 10 (observation, action) pairs / 5560 tokens' in the training section but 'Limited context length (10s)' under limitations. Ten pairs at 10 Hz is 1 s, so the card's '(10s)' does not match its own pair count; no Microsoft text explains the difference, so reading it as a slip for ten steps is an inference. Code defaults agree with ten frames: run_dreaming.py sets context_length 10. · locator: see curator dispositionsource
Rights
component
license
hosting
redistribution
modification
training
Evidence and notes
documentation
unknown
permitted
permitted
unknown
unknown
Applies to this original summary only, not to the cited sources.