Update ReadMe.md

README.md

@@ -9,9 +9,14 @@ tags:
 ---
 [WIP]
 
+Origin repository [JosephusCheung/Qwen-LLaMAfied-7B-Chat](https://huggingface.co/JosephusCheung/Qwen-LLaMAfied-7B-Chat).
+
+
 This is the LLaMAfied version of [Qwen/Qwen-7B-Chat](https://huggingface.co/Qwen/Qwen-7B-Chat), recalibrated to fit the original LLaMA/LLaMA-2-like model structure.
 
-You can use LlamaForCausalLM for model inference, which is the same as LLaMA/LLaMA-2 models (the tokenizer remains the same, so you still need to allow external codes when loading, eg: `AutoTokenizer.from_pretrained(llama_model_path, use_fast=False, trust_remote_code=True)`).
+You can use LlamaForCausalLM for model inference, which is the same as LLaMA/LLaMA-2 models.
+
+I converted the tokenizer from tiktoken format to huggingface format, so you do not need to allow external codes when loading anymore.
 
 The model has been edited to be white-labelled, meaning the model will no longer call itself a Qwen.
 
@@ -22,19 +27,3 @@ PROMPT FORMAT: [chatml](https://github.com/openai/openai-python/blob/main/chatml
 CURRENT MMLU: 50.36
 
 Issue: Compared to the original Qwen-Chat scoring 53.9, the MMLU score dropped slightly (-3.54) due to insufficient realignment.
-
-[在制品]
-
-这是 [通义千问 Qwen/Qwen-7B-Chat](https://huggingface.co/Qwen/Qwen-7B-Chat) 的 LLaMA 化版本，经过重新校准以适应原始的类似 LLaMA/LLaMA-2 的模型结构。
-
-您可以使用 LlamaCausalLM 进行模型推理，和 LLaMA/LLaMA-2 保持一致（分词器保持不变，因此加载时仍然需要允许外部代码，例如：`AutoTokenizer.from_pretrained(llama_model_path, use_fast=False, trust_remote_code=True)`）。
-
-模型已经被编辑实现白标化，不再自称通义千问。
-
-剧透： 进一步的微调正在进行中，当前版本是一个正在进行的工作，一些知识可能由于结构变化而产生偏见和幻觉。 会更新，很快，非常非常非常快。
-
-PROMPT 格式: [chatml](https://github.com/openai/openai-python/blob/main/chatml.md)
-
-当前的 MMLU: 50.36
-
-问题：相比原本的Qwen-Chat的53.9，由于不够充分的重新对齐，MMLU分数略有下降（-3.54）。