YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
llama1-65b: 1 representative decoder layers
Source: huggyllama/llama-65b.
Original text dimensions, context/RoPE and precision settings are retained. Text-only benchmark. No weights are included. Use native SGLang with --load-format dummy.
Published context: 2,048 tokens (max_sequence_length=2048), counting prompt plus generated tokens. Reducing depth does not extend this limit.
| Layer | Source layer (zero-based) | Attention | FFN | PLE |
|---|---|---|---|---|
| 0 | 0 | MHA | dense | no |
Separate MTP modules retained: 0. Ordinary one_batch decoding does not execute MTP.
Run bash llama1-65b-1layer.run from the checkout root on a CUDA machine. See docs/frontier-layer-types.md for native SGLang requirements and layer reasoning. The manifest records provenance; it is not a runtime input.
- Downloads last month
- 15