LouisML/tinyllama_32k

TinyLlama-1.1B-32k

NOTE: This is a fork of the original model at https://huggingface.co/Doctor-Shotgun/TinyLlama-1.1B-32k but with fixed safetensors metadata using the following code:

import safetensors
from safetensors.torch import save_file

tensors = dict()
with safetensors.safe_open(safetensors_path, framework="pt") as f:
    for key in f.keys():
        tensors[key] = f.get_tensor(key)

save_file(tensors, safetensors_path, metadata={'format': 'pt'})

(from https://huggingface.co/SeaLLMs/SeaLLM-7B-Hybrid/discussions/2#65752144412ee70185d49ff5)

Original model card:

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.

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