LLMNewbie commited on
Commit
8999e6a
1 Parent(s): 37bf98d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -1
README.md CHANGED
@@ -5,4 +5,14 @@ language:
5
  - zh
6
  ---
7
 
8
- Pruned language model originated from Vicuna-13B.
 
 
 
 
 
 
 
 
 
 
 
5
  - zh
6
  ---
7
 
8
+ This model is a weight-pruned large language model originated from Vicuna-13B.
9
+ Language model pruning is a technique used to reduce the size and computational requirements of language models,
10
+ making them more efficient for deployment without significantly sacrificing their performance or accuracy.
11
+
12
+ This model uses structured pruning instead of unstructured pruning.
13
+ The structured pruning removes entire units or channels (e.g., neurons, layers, or filter channels in trnasformer).
14
+ This approach can lead to more efficient computational gains since it aligns better with how hardware utilizes data,
15
+ but it may have a more significant impact on model performance.
16
+ However, the unstructured pruning, remove individual weights across the model without regard to the structure of the network.
17
+ While it can lead to significant reductions in model size,
18
+ it may not always translate to speed gains since the resulting sparse matrices might not be efficiently handled by all hardware.