x54-729
commited on
Commit
•
e63eb76
1
Parent(s):
ae3bb61
README
Browse files
README.md
CHANGED
@@ -20,19 +20,19 @@ license: other
|
|
20 |
|
21 |
[![evaluation](https://github.com/InternLM/InternLM/assets/22529082/f80a2a58-5ddf-471a-8da4-32ab65c8fd3b)](https://github.com/internLM/OpenCompass/)
|
22 |
|
23 |
-
[
|
24 |
|
25 |
</div>
|
26 |
|
27 |
|
28 |
## Introduction
|
29 |
-
InternLM2-1.8B is the 1.8 billion parameter version of the second generation InternLM series. In order to facilitate user use and research, InternLM2-1.8B has
|
30 |
|
|
|
|
|
|
|
31 |
|
32 |
-
|
33 |
-
- internlm2-chat: Optimized for conversational interaction on top of the internlm2-chat-sft through RLHF, it excels in instruction adherence, empathetic chatting, and tool invocation.
|
34 |
-
|
35 |
-
The base model of InternLM2 has the following technical features:
|
36 |
|
37 |
- Effective support for ultra-long contexts of up to 200,000 characters: The model nearly perfectly achieves "finding a needle in a haystack" in long inputs of 200,000 characters. It also leads among open-source models in performance on long-text tasks such as LongBench and L-Eval.
|
38 |
- Comprehensive performance enhancement: Compared to the previous generation model, it shows significant improvements in various capabilities, including reasoning, mathematics, and coding.
|
@@ -44,8 +44,8 @@ The base model of InternLM2 has the following technical features:
|
|
44 |
|
45 |
We have evaluated InternLM2 on several important benchmarks using the open-source evaluation tool [OpenCompass](https://github.com/open-compass/opencompass). Some of the evaluation results are shown in the table below. You are welcome to visit the [OpenCompass Leaderboard](https://opencompass.org.cn/rank) for more evaluation results.
|
46 |
|
47 |
-
| Dataset\Models | InternLM2-1.8B | InternLM2-Chat-1.8B | InternLM2-7B | InternLM2-Chat-7B |
|
48 |
-
|
|
49 |
| MMLU | 46.9 | 47.1 | 65.8 | 63.7 |
|
50 |
| AGIEval | 33.4 | 38.8 | 49.9 | 47.2 |
|
51 |
| BBH | 37.5 | 35.2 | 65.0 | 61.2 |
|
@@ -91,12 +91,13 @@ print(output)
|
|
91 |
The code is licensed under Apache-2.0, while model weights are fully open for academic research and also allow **free** commercial usage. To apply for a commercial license, please fill in the [application form (English)](https://wj.qq.com/s2/12727483/5dba/)/[申请表(中文)](https://wj.qq.com/s2/12725412/f7c1/). For other questions or collaborations, please contact <internlm@pjlab.org.cn>.
|
92 |
|
93 |
## 简介
|
94 |
-
书生·浦语-1.8B (InternLM2-1.8B) 是第二代浦语模型系列的18亿参数版本。为了方便用户使用和研究,书生·浦语-1.8B (InternLM2-1.8B)
|
95 |
|
96 |
-
-
|
97 |
-
-
|
|
|
98 |
|
99 |
-
InternLM2
|
100 |
|
101 |
- ��效支持20万字超长上下文:模型在20万字长输入中几乎完美地实现长文“大海捞针”,而且在 LongBench 和 L-Eval 等长文任务中的表现也达到开源模型中的领先水平。
|
102 |
- 综合性能全面提升:各能力维度相比上一代模型全面进步,在推理、数学、代码等方面的能力提升显著。
|
@@ -107,8 +108,8 @@ InternLM2 的基础模型具备以下的技术特点
|
|
107 |
|
108 |
我们使用开源评测工具 [OpenCompass](https://github.com/internLM/OpenCompass/) 对 InternLM2 在几个重要的评测集进行了评测 ,部分评测结果如下表所示,欢迎访问[ OpenCompass 榜单 ](https://opencompass.org.cn/rank)获取更多的评测结果。
|
109 |
|
110 |
-
| 评测集 | InternLM2-1.8B | InternLM2-Chat-1.8B | InternLM2-7B | InternLM2-Chat-7B |
|
111 |
-
|
|
112 |
| MMLU | 46.9 | 47.1 | 65.8 | 63.7 |
|
113 |
| AGIEval | 33.4 | 38.8 | 49.9 | 47.2 |
|
114 |
| BBH | 37.5 | 35.2 | 65.0 | 61.2 |
|
|
|
20 |
|
21 |
[![evaluation](https://github.com/InternLM/InternLM/assets/22529082/f80a2a58-5ddf-471a-8da4-32ab65c8fd3b)](https://github.com/internLM/OpenCompass/)
|
22 |
|
23 |
+
[💻Github Repo](https://github.com/InternLM/InternLM) • [🤔Reporting Issues](https://github.com/InternLM/InternLM/issues/new)
|
24 |
|
25 |
</div>
|
26 |
|
27 |
|
28 |
## Introduction
|
29 |
+
InternLM2-1.8B is the 1.8 billion parameter version of the second generation InternLM series. In order to facilitate user use and research, InternLM2-1.8B has three versions of open-source models. They are:
|
30 |
|
31 |
+
- InternLM2-1.8B: Foundation models with high quality and high adaptation flexibility, which serve as a good starting point for downstream deep adaptations.
|
32 |
+
- InternLM2-Chat-1.8B-SFT: Chat model after supervised fine-tuning (SFT) on InternLM2-1.8B.
|
33 |
+
- InternLM2-Chat-1.8B: Further aligned on top of InternLM2-Chat-1.8B-SFT through online RLHF. InternLM2-Chat-1.8B-SFT exhibits better instruction following, chat experience, and function calling, which is recommended for downstream applications.
|
34 |
|
35 |
+
The InternLM2 has the following technical features:
|
|
|
|
|
|
|
36 |
|
37 |
- Effective support for ultra-long contexts of up to 200,000 characters: The model nearly perfectly achieves "finding a needle in a haystack" in long inputs of 200,000 characters. It also leads among open-source models in performance on long-text tasks such as LongBench and L-Eval.
|
38 |
- Comprehensive performance enhancement: Compared to the previous generation model, it shows significant improvements in various capabilities, including reasoning, mathematics, and coding.
|
|
|
44 |
|
45 |
We have evaluated InternLM2 on several important benchmarks using the open-source evaluation tool [OpenCompass](https://github.com/open-compass/opencompass). Some of the evaluation results are shown in the table below. You are welcome to visit the [OpenCompass Leaderboard](https://opencompass.org.cn/rank) for more evaluation results.
|
46 |
|
47 |
+
| Dataset\Models | InternLM2-1.8B | InternLM2-Chat-1.8B-SFT | InternLM2-7B | InternLM2-Chat-7B |
|
48 |
+
| :---: | :---: | :---: | :---: | :---: |
|
49 |
| MMLU | 46.9 | 47.1 | 65.8 | 63.7 |
|
50 |
| AGIEval | 33.4 | 38.8 | 49.9 | 47.2 |
|
51 |
| BBH | 37.5 | 35.2 | 65.0 | 61.2 |
|
|
|
91 |
The code is licensed under Apache-2.0, while model weights are fully open for academic research and also allow **free** commercial usage. To apply for a commercial license, please fill in the [application form (English)](https://wj.qq.com/s2/12727483/5dba/)/[申请表(中文)](https://wj.qq.com/s2/12725412/f7c1/). For other questions or collaborations, please contact <internlm@pjlab.org.cn>.
|
92 |
|
93 |
## 简介
|
94 |
+
书生·浦语-1.8B (InternLM2-1.8B) 是第二代浦语模型系列的18亿参数版本。为了方便用户使用和研究,书生·浦语-1.8B (InternLM2-1.8B) 共有三个版本的开源模型,他们分别是:
|
95 |
|
96 |
+
- InternLM2-1.8B: 具有高质量和高适应灵活性的基础模型,为下游深度适应提供了良好的起点。
|
97 |
+
- InternLM2-Chat-1.8B-SFT:在 InternLM2-1.8B 上进行监督微调 (SFT) 后得到的对话模型。
|
98 |
+
- InternLM2-chat-1.8B:通过在线 RLHF 在 InternLM2-Chat-1.8B-SFT 之上进一步对齐。 InternLM2-Chat-1.8B-SFT 表现出更好的指令跟随、聊天体验和函数调用,推荐下游应用程序使用。
|
99 |
|
100 |
+
InternLM2 模型具备以下的技术特点
|
101 |
|
102 |
- ��效支持20万字超长上下文:模型在20万字长输入中几乎完美地实现长文“大海捞针”,而且在 LongBench 和 L-Eval 等长文任务中的表现也达到开源模型中的领先水平。
|
103 |
- 综合性能全面提升:各能力维度相比上一代模型全面进步,在推理、数学、代码等方面的能力提升显著。
|
|
|
108 |
|
109 |
我们使用开源评测工具 [OpenCompass](https://github.com/internLM/OpenCompass/) 对 InternLM2 在几个重要的评测集进行了评测 ,部分评测结果如下表所示,欢迎访问[ OpenCompass 榜单 ](https://opencompass.org.cn/rank)获取更多的评测结果。
|
110 |
|
111 |
+
| 评测集 | InternLM2-1.8B | InternLM2-Chat-1.8B-SFT | InternLM2-7B | InternLM2-Chat-7B |
|
112 |
+
| :---: | :---: | :---: | :---: | :---: |
|
113 |
| MMLU | 46.9 | 47.1 | 65.8 | 63.7 |
|
114 |
| AGIEval | 33.4 | 38.8 | 49.9 | 47.2 |
|
115 |
| BBH | 37.5 | 35.2 | 65.0 | 61.2 |
|