LLM Speculative Decoding
Collection
Tiny language models meant to serve as draft models for speculative decoding.
•
6 items
•
Updated
•
2
TinyLlama-1.1B-32k
32k context finetune of TinyLlama-1.1B using increased rope theta (rope frequency base) meant to serve as a long-context speculative decoding model.
Created using TinyLlama-1.1B and further pretraining at 32768 context length on togethercomputer/RedPajama-Data-1T-Sample.
Of note, the base checkpoint used was from commit "final model" fad4f1a5cd0563ac41349b8fec2e6e51156568a0 which was subsequently reverted, and not the current main branch 3T checkpoint of TinyLlama-1.1B.
The quantized model fits alongside a 4.25bpw 70B model at 32k sequence length on a single A6000 and provides noticeable speed-up with speculative decoding.
Wikitext (wikitext-2-raw-v1_train) Perplexity (64 rows) as evaluated via exllamav2:
| Model | 2048 | 4096 | 8192 | 16384 | 32768 |
|---|---|---|---|---|---|
| TinyLlama-1.1B | 8.5633 | 208.3586 | 863.7507 | 1600.5021 | 6981.9021 |
| TinyLlama-1.1B-32k | 8.6548 | 7.8339 | 7.4904 | 7.3674 | 7.1338 |
Evaluation on HumanEval by turboderp:
| Model | Pass@1 | Pass@10 |
|---|---|---|
| TinyLlama-1.1B | 0.0841 | 0.1524 |
| TinyLlama-1.1B (NTK alpha=7.7) | 0.0598 | 0.1098 |
| TinyLlama-1.1B-32k-ckpt-554 | 0.0732 | 0.1402 |
| TinyLlama-1.1B-32k | 0.0829 | 0.1524 |
- Downloads last month
- 693