x54-729 commited on
Commit
f7374de
1 Parent(s): a40ae5d

update readme info

Browse files
Files changed (1) hide show
  1. README.md +6 -6
README.md CHANGED
@@ -29,9 +29,9 @@ license: other
29
  The second generation of the InternLM model, InternLM2, includes models at two scales: 7B and 20B. For the convenience of users and researchers, we have open-sourced four versions of each scale of the model, which are:
30
 
31
  - internlm2-base: A high-quality and highly adaptable model base, serving as an excellent starting point for deep domain adaptation.
32
- - internlm2 (**recommended**): Built upon the internlm2-base, this version has been enhanced in multiple capability directions. It shows outstanding performance in evaluations while maintaining robust general language abilities, making it our recommended choice for most applications.
33
- - internlm2-sft: Based on the Base model, it undergoes supervised human alignment training.
34
- - internlm2-chat (**recommended**): Optimized for conversational interaction on top of the internlm2-sft through RLHF, it excels in instruction adherence, empathetic chatting, and tool invocation.
35
 
36
  The base model of InternLM2 has the following technical features:
37
 
@@ -95,9 +95,9 @@ The code is licensed under Apache-2.0, while model weights are fully open for ac
95
  第二代浦语模型, InternLM2 包含 7B 和 20B 两个量级的模型。为了方便用户使用和研究,每个量级的模型我们总共开源了四个版本的模型,他们分别是
96
 
97
  - internlm2-base: 高质量和具有很强可塑性的模型基座,是模型进行深度领域适配的高质量起点;
98
- - internlm2(**推荐**): 在internlm2-base基础上,在多个能力方向进行了强化,在评测中成绩优异,同时保持了很好的通用语言能力,是我们推荐的在大部分应用中考虑选用的优秀基座;
99
- - internlm2-sft:在Base基础上,进行有监督的人类对齐训练;
100
- - internlm2-chat(**推荐**):在internlm2-sft基础上,经过RLHF,面向对话交互进行了优化,具有很好的指令遵循、共情聊天和调用工具等的能力。
101
 
102
  InternLM2 的基础模型具备以下的技术特点
103
 
 
29
  The second generation of the InternLM model, InternLM2, includes models at two scales: 7B and 20B. For the convenience of users and researchers, we have open-sourced four versions of each scale of the model, which are:
30
 
31
  - internlm2-base: A high-quality and highly adaptable model base, serving as an excellent starting point for deep domain adaptation.
32
+ - internlm2 (**recommended**): Built upon the internlm2-base, this version has further pretrained on domain-specific corpus. It shows outstanding performance in evaluations while maintaining robust general language abilities, making it our recommended choice for most applications.
33
+ - internlm2-chat-sft: Based on the Base model, it undergoes supervised human alignment training.
34
+ - internlm2-chat (**recommended**): Optimized for conversational interaction on top of the internlm2-chat-sft through RLHF, it excels in instruction adherence, empathetic chatting, and tool invocation.
35
 
36
  The base model of InternLM2 has the following technical features:
37
 
 
95
  第二代浦语模型, InternLM2 包含 7B 和 20B 两个量级的模型。为了方便用户使用和研究,每个量级的模型我们总共开源了四个版本的模型,他们分别是
96
 
97
  - internlm2-base: 高质量和具有很强可塑性的模型基座,是模型进行深度领域适配的高质量起点;
98
+ - internlm2(**推荐**): 在internlm2-base基础上,进一步在特定领域的语料上进行预训练,在评测中成绩优异,同时保持了很好的通用语言能力,是我们推荐的在大部分应用中考虑选用的优秀基座;
99
+ - internlm2-chat-sft:在Base基础上,进行有监督的人类对齐训练;
100
+ - internlm2-chat(**推荐**):在internlm2-chat-sft基础上,经过RLHF,面向对话交互进行了优化,具有很好的指令遵循、共情聊天和调用工具等的能力。
101
 
102
  InternLM2 的基础模型具备以下的技术特点
103