anonymitaet
commited on
Update README.md
Browse files
README.md
CHANGED
@@ -4,16 +4,16 @@ license: apache-2.0
|
|
4 |
<div align="center">
|
5 |
|
6 |
<picture>
|
7 |
-
<img
|
8 |
</picture>
|
9 |
|
10 |
</div>
|
11 |
|
12 |
<p align="center">
|
13 |
-
<a href="https://github.com/01-ai
|
14 |
<a href="https://discord.gg/hYUwWddeAu">πΎ Discord</a> β’
|
15 |
<a href="https://twitter.com/01ai_yi">π€ Twitter</a> β’
|
16 |
-
<a href="https://github.com/01-ai/Yi/issues/
|
17 |
<br/>
|
18 |
<a href="https://arxiv.org/abs/2403.04652">π Paper</a> β’
|
19 |
<a href="https://github.com/01-ai/Yi/tree/main?tab=readme-ov-file#faq">π FAQ</a> β’
|
@@ -36,54 +36,52 @@ Model | Context Length | Pre-trained Tokens
|
|
36 |
|
37 |
# Models
|
38 |
|
39 |
-
|
40 |
-
|
41 |
-
<
|
42 |
-
|
43 |
-
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
|
48 |
-
|
49 |
-
</
|
50 |
-
|
51 |
-
-
|
52 |
-
|
53 |
-
<
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
-
Yi-1.5-
|
58 |
-
|
59 |
-
|
60 |
-
|
61 |
-
</
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
62 |
|
63 |
# Benchmarks
|
64 |
|
65 |
- Chat models
|
66 |
|
67 |
-
|
68 |
|
|
|
69 |
|
70 |
-
-
|
71 |
-
|
72 |
-
- Yi-1.5-34B excels beyond or is on par with some larger models in overall performance.
|
73 |
|
74 |
-
|
75 |
|
76 |
-
|
77 |
-
|
78 |
-
| Model | MMLU | CMMLU | BBH | AGIEval | HumanEval(+) | MBPP(+) | GSM8k | Math |
|
79 |
-
| -------------- | ---- | ----- | ---- | ------- | ------------ | ---------- | ----- | ----- |
|
80 |
-
| Gemma-7B | 64.3 | 48.4 | 41.1 | 46.0 | 33.5(28.0) | 45.8(32.8) | 55.7 | 24.8 |
|
81 |
-
| Qwen1.5-7B | 61.0 | 73.4 | 33.4 | 61.6 | 36.0(31.1) | 46.1(37.6) | 70.1 | 20.3 |
|
82 |
-
| Mistral-7B | 62.5 | 44.6 | 45.0 | 42.4 | 29.3(22.6) | 50.2(32.1) | 47.5 | 15.5 |
|
83 |
-
| Mistral 8\*7B | 70.6 | 53.0 | 52.4 | 49.5 | 40.2(31.1) | 60.7(31.1) | 65.7 | 28.4 |
|
84 |
-
| Llama3-8B_Base | 66.6 | 50.9 | 47.9 | 44.7 | 34.7(31.7) | 48.0(44.9) | 54.7 | 21.16 |
|
85 |
-
| Yi 1.5-6B | 63.5 | 70.8 | 45.7 | 56.0 | 36.5(28.7) | 56.8(46.9) | 62.2 | 28.42 |
|
86 |
-
| Yi 1.5-9B | 69.5 | 74.8 | 50.9 | 62.7 | 41.4(34.1) | 61.1(53.6) | 73.7 | 32.6 |
|
87 |
|
88 |
# Quick Start
|
89 |
|
|
|
4 |
<div align="center">
|
5 |
|
6 |
<picture>
|
7 |
+
<img src="https://raw.githubusercontent.com/01-ai/Yi/main/assets/img/Yi_logo_icon_light.svg" width="150px">
|
8 |
</picture>
|
9 |
|
10 |
</div>
|
11 |
|
12 |
<p align="center">
|
13 |
+
<a href="https://github.com/01-ai">π GitHub</a> β’
|
14 |
<a href="https://discord.gg/hYUwWddeAu">πΎ Discord</a> β’
|
15 |
<a href="https://twitter.com/01ai_yi">π€ Twitter</a> β’
|
16 |
+
<a href="https://github.com/01-ai/Yi-1.5/issues/2">π¬ WeChat</a>
|
17 |
<br/>
|
18 |
<a href="https://arxiv.org/abs/2403.04652">π Paper</a> β’
|
19 |
<a href="https://github.com/01-ai/Yi/tree/main?tab=readme-ov-file#faq">π FAQ</a> β’
|
|
|
36 |
|
37 |
# Models
|
38 |
|
39 |
+
<table>
|
40 |
+
<thead>
|
41 |
+
<tr>
|
42 |
+
<th>Model</th>
|
43 |
+
<th>Name</th>
|
44 |
+
<th>Download</th>
|
45 |
+
</tr>
|
46 |
+
</thead>
|
47 |
+
<tbody>
|
48 |
+
<tr>
|
49 |
+
<td rowspan="3">Chat</td>
|
50 |
+
<td>Yi-1.5-34B-Chat</td>
|
51 |
+
<td rowspan="6">β’ <a href="https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8">π€ Hugging Face</a> β’ <a href="https://www.modelscope.cn/organization/01ai/">π€ ModelScope</a><br></td>
|
52 |
+
</tr>
|
53 |
+
<tr>
|
54 |
+
<td>Yi-1.5-9B-Chat</td>
|
55 |
+
</tr>
|
56 |
+
<tr>
|
57 |
+
<td>Yi-1.5-6B-Chat</td>
|
58 |
+
</tr>
|
59 |
+
<tr>
|
60 |
+
<td rowspan="3">Base</td>
|
61 |
+
<td>Yi-1.5-34B-Chat</td>
|
62 |
+
</tr>
|
63 |
+
<tr>
|
64 |
+
<td>Yi-1.5-9B-Chat</td>
|
65 |
+
</tr>
|
66 |
+
<tr>
|
67 |
+
<td>Yi-1.5-6B-Chat</td>
|
68 |
+
</tr>
|
69 |
+
</tbody>
|
70 |
+
</table>
|
71 |
|
72 |
# Benchmarks
|
73 |
|
74 |
- Chat models
|
75 |
|
76 |
+
Yi-1.5-34B-Chat is on par with or excels beyond larger models in most benchmarks.
|
77 |
|
78 |
+
tbd
|
79 |
|
80 |
+
Yi-1.5-9B-Chat is a strong performer among similarly sized open-source models.
|
|
|
|
|
81 |
|
82 |
+
tbd
|
83 |
|
84 |
+
- Base models
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
85 |
|
86 |
# Quick Start
|
87 |
|