naxautify/pythia-1.4b-deduped-8k
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: naxautify/pythia-1.4b-deduped-8k
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-23 18:36:12 +08:00
commit ba39edf434
21 changed files with 101396 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
README.md Normal file
View File

@@ -0,0 +1,10 @@
---
datasets:
- EleutherAI/the_pile_deduplicated
pipeline_tag: text-generation
library_name: transformers
---
# Pythia 1.4b Deduped with 8k Context Window
This model fine-tunes Pythia 1.4b model with a context window of 8k tokens. With optimizations like Flash Attention & bitsandbytes, I could fit the model the entire model with a batch size of 1, on a single A100 (40 GB). The fine-tuning took ~30 hours, after which the loss was similar to that of fine-tuning at the context window of 2k tokens.