Update README.md

README.md

@@ -15,11 +15,11 @@ language:
 <em>[Paper][Code][🤗] (would be released soon)</em>
 </p>
 
-Infinity-Instruct-7M-0729-Llama3.1-70B is an opensource supervised instruction tuning model without reinforcement learning from human feedback (RLHF). This model is just finetuned on [Infinity-Instruct-7M and Infinity-Instruct-0729](https://huggingface.co/datasets/BAAI/Infinity-Instruct) and showing favorable results on AlpacaEval 2.0 and arena-hard compared to GPT4.
+Infinity-Instruct-7M-Gen-Llama3.1-70B is an opensource supervised instruction tuning model without reinforcement learning from human feedback (RLHF). This model is just finetuned on [Infinity-Instruct-7M and Infinity-Instruct-Gen](https://huggingface.co/datasets/BAAI/Infinity-Instruct) and showing favorable results on AlpacaEval 2.0 and arena-hard compared to GPT4.
 
 ## **News**
 
-- 🔥🔥🔥[2024/08/02] We release the model weights of [InfInstruct-Llama3.1-70B 0729](https://huggingface.co/BAAI/Infinity-Instruct-7M-0729-Llama3_1-70B), [InfInstruct-Llama3.1-8B 0729](https://huggingface.co/BAAI/Infinity-Instruct-7M-0729-Llama3_1-8B), [InfInstruct-Mistral-7B 0729](https://huggingface.co/BAAI/Infinity-Instruct-7M-0729-Mistral-7B).
+- 🔥🔥🔥[2024/08/02] We release the model weights of [InfInstruct-Llama3.1-70B Gen](https://huggingface.co/BAAI/Infinity-Instruct-7M-Gen-Llama3_1-70B), [InfInstruct-Llama3.1-8B Gen](https://huggingface.co/BAAI/Infinity-Instruct-7M-Gen-Llama3_1-8B), [InfInstruct-Mistral-7B Gen](https://huggingface.co/BAAI/Infinity-Instruct-7M-Gen-Mistral-7B).
 
 - 🔥🔥🔥[2024/08/02] We release the 7M foundational dataset [Infinity-Instruct-7M](https://huggingface.co/datasets/BAAI/Infinity-Instruct).
 
@@ -39,7 +39,7 @@ Infinity-Instruct-7M-0729-Llama3.1-70B is an opensource supervised instruction t
 <img src="fig/trainingflow.png">
 </p>
 
-Infinity-Instruct-7M-0729-Llama3.1-70B is tuned on Million-level instruction dataset [Infinity-Instruct](https://huggingface.co/datasets/BAAI/Infinity-Instruct). First, we apply the foundational dataset Infinity-Instruct-7M to improve the foundational ability (math & code) of Llama3.1-70B, and get the foundational instruct model Infinity-Instruct-7M-Llama3-70B. Then we finetune the Infinity-Instruct-7M-Llama3-70B to get the stronger chat model Infinity-Instruct-7M-0729-Llama3_1-70B. Here is the training hyperparamers. 
+Infinity-Instruct-7M-Gen-Llama3.1-70B is tuned on Million-level instruction dataset [Infinity-Instruct](https://huggingface.co/datasets/BAAI/Infinity-Instruct). First, we apply the foundational dataset Infinity-Instruct-7M to improve the foundational ability (math & code) of Llama3.1-70B, and get the foundational instruct model Infinity-Instruct-7M-Llama3-70B. Then we finetune the Infinity-Instruct-7M-Llama3-70B to get the stronger chat model Infinity-Instruct-7M-Gen-Llama3_1-70B. Here is the training hyperparamers. 
 
 ```bash
 epoch: 3
@@ -70,13 +70,13 @@ Thanks to [FlagScale](https://github.com/FlagOpen/FlagScale), we could concatena
 | **InfInstruct-7M-Llama-3.1-8B**   |      **8.2**     |        **33.9**       |        **30.4**       |
 | InfInstruct-3M-0613-Llama-3-70B |      8.7     |        31.5       |        --       |
 | InfInstruct-3M-0625-Llama-3-70B |      8.9     |        38.0       |        --       |
-| **InfInstruct-3M-0729-Llama-3.1-70B** |      **8.9**     |        **46.1**       |        **66.0**       |
+| **InfInstruct-3M-Gen-Llama-3.1-70B** |      **8.9**     |        **46.1**       |        **66.0**       |
 
 *denote the model is finetuned without reinforcement learning from human feedback (RLHF). 
 
 ## **How to use**
 
-Infinity-Instruct-7M-0729-Llama3_1-70B adopt the same chat template of [Llama3-70B-instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct):
+Infinity-Instruct-7M-Gen-Llama3_1-70B adopt the same chat template of [Llama3-70B-instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct):
 
 ```bash
 <|begin_of_text|><|start_header_id|>user<|end_header_id|>
@@ -95,11 +95,11 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, LogitsProcessorLis
 import torch
 device = "cuda" # the device to load the model onto
 
-model = AutoModelForCausalLM.from_pretrained("BAAI/Infinity-Instruct-7M-0729-Llama3_1-70B",
+model = AutoModelForCausalLM.from_pretrained("BAAI/Infinity-Instruct-7M-Gen-Llama3_1-70B",
     torch_dtype=torch.bfloat16,
     device_map="auto"
 )
-tokenizer = AutoTokenizer.from_pretrained("BAAI/Infinity-Instruct-7M-0729-Llama3_1-70B")
+tokenizer = AutoTokenizer.from_pretrained("BAAI/Infinity-Instruct-7M-Gen-Llama3_1-70B")
 
 prompt = "Give me a short introduction to large language model."
 messages = [