update README.md

README.md

@@ -23,11 +23,11 @@ Results in [ChatRAG Bench](https://huggingface.co/datasets/nvidia/ChatRAG-Bench)
 
 
 ![Example Image](overview.png)
-| | ChatQA-2-70B | GPT-4-Turbo-2024-04-09 | Qwen2-72B-Instruct | Llama3.1-70B-Instruct |
+<!-- | | ChatQA-2-70B | GPT-4-Turbo-2024-04-09 | Qwen2-72B-Instruct | Llama3.1-70B-Instruct |
 | -- |:--:|:--:|:--:|:--:|
 | Ultra-long (4k) | 41.04 | 33.16 | 39.77 | 39.81 |
 | Long (32k) | 48.15 | 51.93 | 49.94 | 49.92 |
-| Short (4k) | 56.30 | 54.72 | 54.06 | 52.12 |
+| Short (4k) | 56.30 | 54.72 | 54.06 | 52.12 | -->
 
 Note that ChatQA-2 is built based on Llama-3 base model.
 
@@ -65,7 +65,7 @@ Assistant:
 <pre>
 This is a chat between a user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions based on the context. The assistant should also indicate when the answer cannot be found in the context.
 </pre>
-**Note that our ChatQA-1.5 models are optimized for the capability with context, e.g., over documents or retrieved context.**
+**Note that our ChatQA-2 models are optimized for the capability with context, e.g., over documents or retrieved context.**
 
 ## How to use
 
@@ -75,7 +75,7 @@ This can be applied to the scenario where the whole document can be fitted into
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 
-model_id = "nvidia/Llama3-ChatQA-1.5-8B"
+model_id = "nvidia/Llama3-ChatQA-2-8B"
 
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")