change name

README.md

@@ -11,19 +11,21 @@ language:
 
 **The Faro chat model focuses on practicality and long-context modeling. It handles various downstream tasks with higher quality, delivering stable and reliable results even when inputs contain lengthy documents or complex instructions. Faro seamlessly works in both English and Chinese.**
 
-# Faro-Qwen-4B-100K
-Faro-Qwen-4B-100K is an improved [Qwen/Qwen1.5-4B-Chat](https://huggingface.co/Qwen/Qwen1.5-4B-Chat) with extensive instruction tuning on [Fusang-V1](https://huggingface.co/datasets/wenbopan/Fusang-v1). Compared to Qwen1.5-4B-Chat, Faro-Qwen-4B-100K has gained greater capability in various downstream tasks and long-context modeling thanks to the large-scale synthetic data in Fusang-V1. Faro-Qwen-4B-100K use dynamic NTK and continual training to extend its max context length to 100K.
+# Faro-Qwen-4B
+Faro-Qwen-4B is an improved [Qwen/Qwen1.5-4B-Chat](https://huggingface.co/Qwen/Qwen1.5-4B-Chat) with extensive instruction tuning on [Fusang-V1](https://huggingface.co/datasets/wenbopan/Fusang-v1). Compared to Qwen1.5-4B-Chat, Faro-Qwen-4B has gained greater capability in various downstream tasks and long-context modeling thanks to the large-scale synthetic data in Fusang-V1. 
+
+Faro-Qwen-4B uses dynamic NTK and continual training to extend its max context length to 100K. However, due to the lack of Dynamic NTK supports for`Qwen2ForCausalLM` in vLLM, inference on text longer than 32K requires using native `transformers` implementations.
 
 ## How to Use
 
-Faro-Qwen-4B-100K uses chatml template. I recommend using vLLM for long inputs.
+Faro-Qwen-4B uses chatml template. I recommend using vLLM for long inputs.
 
 ```python
 import io
 import requests
 from PyPDF2 import PdfReader
 from vllm import LLM, SamplingParams
-llm = LLM(model="wenbopan/Faro-Qwen-4B-100K")
+llm = LLM(model="wenbopan/Faro-Qwen-4B")
 pdf_data = io.BytesIO(requests.get("https://arxiv.org/pdf/2303.08774.pdf").content)
 document = "".join(page.extract_text() for page in PdfReader(pdf_data).pages) # 100 pages
 question = f"{document}\n\nAccording to the paper, what is the parameter count of GPT-4?"
@@ -37,8 +39,8 @@ print(output[0].outputs[0].text)
 
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
-model = AutoModelForCausalLM.from_pretrained('wenbopan/Faro-Qwen-4B-100K', device_map="cuda")
-tokenizer = AutoTokenizer.from_pretrained('wenbopan/Faro-Qwen-4B-100K')
+model = AutoModelForCausalLM.from_pretrained('wenbopan/Faro-Qwen-4B', device_map="cuda")
+tokenizer = AutoTokenizer.from_pretrained('wenbopan/Faro-Qwen-4B')
 messages = [
     {"role": "system", "content": "You are a helpful assistant. Always answer with a short response."},
     {"role": "user", "content": "Tell me what is Pythagorean theorem like you are a pirate."}
@@ -50,4 +52,4 @@ response = tokenizer.decode(generated_ids[0], skip_special_tokens=True)
 
 </details>
 
-For more info please refer to [wenbopan/Faro-Yi-9B-200K](https://huggingface.co/wenbopan/Faro-Yi-9B-200K)
+For more info please refer to [wenbopan/Faro-Yi-9B](https://huggingface.co/wenbopan/Faro-Yi-9B)