fix typos

README.md

@@ -13,7 +13,7 @@ pipeline_tag: text-generation
 
 # Dataset Card for Faro-Yi-9B-DPO
 
-This is the DPO version of [wenbopan/Faro-Yi-9B](https://huggingface.co/wenbopan/Faro-Yi-9B). Compared to Faro-Yi-9B and [Yi-9B-200K](https://huggingface.co/01-ai/Yi-9B-200K), the DPO model excel at many tasks, surpass the original Yi-9B-200K by a large margin.
+This is the DPO version of [wenbopan/Faro-Yi-9B](https://huggingface.co/wenbopan/Faro-Yi-9B). Compared to Faro-Yi-9B and [Yi-9B-200K](https://huggingface.co/01-ai/Yi-9B-200K), the DPO model excels at many tasks, surpassing the original Yi-9B-200K by a large margin.
 
 | **Metric**      | **MMLU**  | GSM8K     | **hellaswag** | **truthfulqa** | **ai2_arc** | **winogrande** | **CMMLU** |
 | --------------- | --------- | --------- | ------------- | -------------- | ----------- | -------------- | --------- |
@@ -24,9 +24,6 @@ This is the DPO version of [wenbopan/Faro-Yi-9B](https://huggingface.co/wenbopan
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/62cd3a3691d27e60db0698b0/Oa9QSbXgaYVekrYfgfaiC.png)
 
-## How to Use
-
-
 ## How to Use
 
 Faro-Yi-9B-DPO uses the chatml template and performs well in both short and long contexts. For longer inputs under **24GB of VRAM**, I recommend to use vLLM to have a max prompt of 32K. Setting `kv_cache_dtype="fp8_e5m2"` allows for 48K input length. 4bit-AWQ quantization on top of that can boost input length to 160K, albeit with some performance impact. Adjust `max_model_len` arg in vLLM or `config.json` to avoid OOM.