Josephgflowers/Tinyllama-616M-Cinder
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: Josephgflowers/Tinyllama-616M-Cinder
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-24 22:55:12 +08:00
commit 18f95e6d36
15 changed files with 295 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
README.md Normal file
View File

@@ -0,0 +1,7 @@
---
license: mit
---
I cut my TinyLlama 1.1B cinder v 2 down from 22 layers to 14. At 14 there was no coherent text but there were emerging ideas of a response.
I then trained on the Reason with Cinder dataset and prunned the model again to 11 layers and only emerging responses. I then trained on a subset of open orca, sharegpt, cinder again, and tiny textbooks.
I am putting it up as a base model that may need work. If you continue training please let me know on the tinyllama discord, I have some interesting plans for this model.
I use the Zephyr chat format.