JustinLin610 commited on
Commit
a9f04bc
1 Parent(s): 4cf4e56

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -3
README.md CHANGED
@@ -15,14 +15,12 @@ tags:
15
 
16
  ## Introduction
17
 
18
- Qwen1.5-MoE is the beta version of Qwen2-MoE, a transformer-based decoder-only language model pretrained on a large amount of data.
19
 
20
  For more details, please refer to our [blog post](https://qwenlm.github.io/blog/qwen1.5/) and [GitHub repo](https://github.com/QwenLM/Qwen1.5).
21
 
22
 
23
  ## Model Details
24
- Qwen1.5-MoE is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and code. For the beta version, temporarily we did not include GQA and the mixture of SWA and full attention.
25
-
26
  Qwen1.5-MoE employs Mixture of Experts (MoE) architecture, where the models are upcycled from dense language models. For instance, `Qwen1.5-MoE-A2.7B` is upcycled from `Qwen-1.8B`. It has 14.3B parameters in total and 2.7B activated parameters during runtime, while achieching comparable performance to `Qwen1.5-7B`, it only requires 20% of the training resources. We also observed that the inference speed is 1.8 times that of `Qwen1.5-7B`.
27
 
28
  ## Training details
 
15
 
16
  ## Introduction
17
 
18
+ Qwen1.5-MoE is a transformer-based MoE decoder-only language model pretrained on a large amount of data.
19
 
20
  For more details, please refer to our [blog post](https://qwenlm.github.io/blog/qwen1.5/) and [GitHub repo](https://github.com/QwenLM/Qwen1.5).
21
 
22
 
23
  ## Model Details
 
 
24
  Qwen1.5-MoE employs Mixture of Experts (MoE) architecture, where the models are upcycled from dense language models. For instance, `Qwen1.5-MoE-A2.7B` is upcycled from `Qwen-1.8B`. It has 14.3B parameters in total and 2.7B activated parameters during runtime, while achieching comparable performance to `Qwen1.5-7B`, it only requires 20% of the training resources. We also observed that the inference speed is 1.8 times that of `Qwen1.5-7B`.
25
 
26
  ## Training details