HenryHHHH commited on
Commit
c73afa8
·
verified ·
1 Parent(s): 2e09c9c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +25 -0
README.md CHANGED
@@ -1,3 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ### Overview
2
 
3
  This model is a distilled version of LLaMA 2, containing approximately 80 million parameters. It was trained using a mix of OpenWebText and WikiText Raw V1 datasets. Knowledge distillation was employed to transfer knowledge from a larger "teacher" model—Meta’s 7B LLaMA 2—to help this smaller model mimic the behavior of the teacher.
 
1
+ ---
2
+ language: en
3
+ tags:
4
+ - text-generation
5
+ - knowledge-distillation
6
+ - llama
7
+ - causal-lm
8
+ - openwebtext
9
+ - wikitext
10
+ - transfer-learning
11
+ model_name: DistilLLaMA
12
+ license: apache-2.0
13
+ datasets:
14
+ - openwebtext
15
+ - wikitext
16
+ parameter_count: 80M
17
+ metrics:
18
+ - cosine-similarity
19
+ - exact-match
20
+ - rouge
21
+ library_name: transformers
22
+ base_model: meta-llama/LLaMA-2-7B
23
+ ---
24
+
25
+
26
  ### Overview
27
 
28
  This model is a distilled version of LLaMA 2, containing approximately 80 million parameters. It was trained using a mix of OpenWebText and WikiText Raw V1 datasets. Knowledge distillation was employed to transfer knowledge from a larger "teacher" model—Meta’s 7B LLaMA 2—to help this smaller model mimic the behavior of the teacher.