Safetensors
granitemoehybrid
ramendik commited on
Commit
d4ffca8
·
verified ·
1 Parent(s): 65ccdda

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -2,12 +2,13 @@
2
  license: apache-2.0
3
  datasets:
4
  - ramendik/kimify-ifeval-like
 
5
  base_model:
6
  - ibm-granite/granite-4.0-h-1b
7
  ---
8
 
9
  Testing checkpoint of an attempt at distilling the style of Kimi K2 Instruct, inasmuch as possible in this size, by fine-tuning Granite 4.0 h 1b.
10
 
11
- Long sequences made Granite prone to looping, so I made several kimi-generated datasets system-prompted for brevity then filtered at max 1000t single asssistant response. Of these only one is published but I'll put more up soon.
12
 
13
  This is clearly not the final checkpoint but I'd appreciate testing to see what needs to be improved.
 
2
  license: apache-2.0
3
  datasets:
4
  - ramendik/kimify-ifeval-like
5
+ - ramendik/kimify-short-20260131
6
  base_model:
7
  - ibm-granite/granite-4.0-h-1b
8
  ---
9
 
10
  Testing checkpoint of an attempt at distilling the style of Kimi K2 Instruct, inasmuch as possible in this size, by fine-tuning Granite 4.0 h 1b.
11
 
12
+ Long sequences made Granite prone to looping, so I made kimi-generated datasets system-prompted for brevity then filtered at max 1000t single asssistant response.
13
 
14
  This is clearly not the final checkpoint but I'd appreciate testing to see what needs to be improved.