eid-growing-state-360m-6k is a model from Jerry Liu (access requested at publisher). Its published files total 14.6 GB.
Memory Caching SSC with 2, 4, or 8 recurrent states. All use seed 1111, 6,000 optimizer steps, a global batch of 256 at sequence length 2,048 (3,145,728,000 training tokens), and a 4× rare-recall loss weight. The tokenization is GPT-2.
Model Card
Memory Caching SSC with 2, 4, or 8 recurrent states. All use seed 1111, 6,000 optimizer steps, a global batch of 256 at sequence length 2,048 (3,145,728,000 training tokens), and a 4× rare-recall loss weight. The tokenization is GPT-2. See manifest.json for the exact checkpoint, resolved-config, evaluator, and cohort identities. These files require the project-specific model implementation. They are not Transformers AutoModel checkpoints. The training source is The evaluation source is which preserves those model implementations and adds the named full suites. Run SWDE on all 1,111 examples and SQuAD completion on all 2,984 examples for each of the nine checkpoints. The eval/ folder…
Excerpt from the card by Jerry Liu.
Identity and Version
- Repository
- jwl50-stanford/eid-growing-state-360m-6k
- Publisher
- Jerry Liu
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- en
- Revision
- 882a5210b65930859deec4a229812c214b695130
- First published
- 2026-09-26
- Last updated
- 2026-09-26
Files and Weights
34 files, 14.6 GB in total. The weights are 9 files totalling 14.6 GB in pt.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| grm_s2/final-weights.pt | Weights | 1.6 GB | — |
| grm_s4/final-weights.pt | Weights | 1.6 GB | — |
| grm_s8/final-weights.pt | Weights | 1.6 GB | — |
| paper_s2/final-weights.pt | Weights | 1.6 GB | — |
| paper_s4/final-weights.pt | Weights | 1.6 GB | — |
| paper_s8/final-weights.pt | Weights | 1.6 GB | — |
| ssc_s2/final-weights.pt | Weights | 1.6 GB | — |
| ssc_s4/final-weights.pt | Weights | 1.6 GB | — |
| ssc_s8/final-weights.pt | Weights | 1.6 GB | — |
| configs/grm_s2.yaml | Configuration | 6.1 KB | — |
| configs/grm_s4.yaml | Configuration | 6.1 KB | — |
| configs/grm_s8.yaml | Configuration | 6.1 KB | — |
| configs/paper_s2.yaml | Configuration | 6.1 KB | — |
| configs/paper_s4.yaml | Configuration | 6.1 KB | — |
| configs/paper_s8.yaml | Configuration | 6.1 KB | — |
| configs/ssc_s2.yaml | Configuration | 6.2 KB | — |
| configs/ssc_s4.yaml | Configuration | 6.2 KB | — |
| configs/ssc_s8.yaml | Configuration | 6.2 KB | — |
| eval/cohorts/squad_completion.json | Configuration | 885.4 KB | — |
| eval/cohorts/swde.json | Configuration | 329.1 KB | — |
| eval/squad_completion_full.yaml | Configuration | 222 B | — |
| eval/swde_full.yaml | Configuration | 186 B | — |
| grm_s2/artifact.json | Configuration | 673 B | — |
| grm_s4/artifact.json | Configuration | 673 B | — |
| grm_s8/artifact.json | Configuration | 673 B | — |
| manifest.json | Configuration | 6.2 KB | — |
| paper_s2/artifact.json | Configuration | 679 B | — |
| paper_s4/artifact.json | Configuration | 679 B | — |
| paper_s8/artifact.json | Configuration | 680 B | — |
| ssc_s2/artifact.json | Configuration | 673 B | — |
| ssc_s4/artifact.json | Configuration | 673 B | — |
| ssc_s8/artifact.json | Configuration | 673 B | — |
| README.md | Documentation | 3.3 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Access requested at publisher
- Download size
- 14.6 GB
Jerry Liu grants access through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 14.6 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.