Update README.md

README.md

@@ -28,7 +28,7 @@ Qwen1.5-MoE employs Mixture of Experts (MoE) architecture, where the models are
 We pretrained the models with a large amount of data, and we post-trained the models with both supervised finetuning and direct preference optimization. However, DPO leads to improvements in human preference evaluation but degradation in benchmark evaluation. In the very near future, we will fix both problems.
 
 ## Requirements
-The code of Qwen1.5-MoE has been in the latest Hugging face transformers and we advise you to install `transformers>=4.39.0`, or you might encounter the following error:
+The code of Qwen1.5-MoE has been in the latest Hugging face transformers and we advise you to build from source with command `pip install git+https://github.com/huggingface/transformers`, or you might encounter the following error:
 ```
 KeyError: 'qwen2_moe'.
 ```
@@ -71,7 +71,7 @@ generated_ids = [
 response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
 ```
 
-For quantized models, we advise you to use the GPTQ, AWQ, and GGUF correspondents, namely `Qwen1.5-MoE-A2.7B-Chat-GPTQ-Int4`, `Qwen1.5-MoE-A2.7B-Chat-GPTQ-Int8`, `Qwen1.5-MoE-A2.7B-Chat-AWQ`, and `Qwen1.5-MoE-A2.7B-Chat-GGUF`.
+For quantized models, we advise you to use the GPTQ correspondents, namely `Qwen1.5-MoE-A2.7B-Chat-GPTQ-Int4`.
 
 
 ## Tips