pr4nav101 commited on
Commit
667ab0b
·
verified ·
1 Parent(s): a76493d

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +18 -0
README.md ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ datasets:
4
+ - pr4nav101/COT_TTM_Finetuning
5
+ language:
6
+ - en
7
+ base_model:
8
+ - unsloth/Llama-3.2-1B-Instruct-bnb-4bit
9
+ - pr4nav101/llama-3-8b-Instruct-bnb-4bit-Tiny-Thought-Model-Large
10
+ pipeline_tag: text-generation
11
+ library_name: peft
12
+ tags:
13
+ - COT
14
+ - TTM
15
+ - LLM
16
+ method:
17
+ - Knowledge Distillation with Reverse KL Divergence + PEFT Finetuning
18
+ ---