munish0838
commited on
Commit
β’
6e374a4
1
Parent(s):
409fde8
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
library_name: transformers
|
4 |
+
pipeline_tag: text-generation
|
5 |
+
tags:
|
6 |
+
- llama
|
7 |
+
base_model: 01-ai/Yi-1.5-9B-32K
|
8 |
+
---
|
9 |
+
|
10 |
+
# Yi-1.5-9B-32K-GGUF
|
11 |
+
- This is quantized version of [01-ai/Yi-1.5-9B-32K](https://huggingface.co/01-ai/Yi-1.5-9B-32K) created using llama.cpp
|
12 |
+
|
13 |
+
# Model Description
|
14 |
+
|
15 |
+
Yi-1.5 is an upgraded version of Yi. It is continuously pre-trained on Yi with a high-quality corpus of 500B tokens and fine-tuned on 3M diverse fine-tuning samples.
|
16 |
+
|
17 |
+
Compared with Yi, Yi-1.5 delivers stronger performance in coding, math, reasoning, and instruction-following capability, while still maintaining excellent capabilities in language understanding, commonsense reasoning, and reading comprehension.
|
18 |
+
|
19 |
+
<div align="center">
|
20 |
+
|
21 |
+
Model | Context Length | Pre-trained Tokens
|
22 |
+
| :------------: | :------------: | :------------: |
|
23 |
+
| Yi-1.5 | 4K, 16K, 32K | 3.6T
|
24 |
+
|
25 |
+
</div>
|
26 |
+
|
27 |
+
# Models
|
28 |
+
|
29 |
+
- Chat models
|
30 |
+
|
31 |
+
<div align="center">
|
32 |
+
|
33 |
+
| Name | Download |
|
34 |
+
| --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
35 |
+
| Yi-1.5-34B-Chat | β’ [π€ Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) β’ [π€ ModelScope](https://www.modelscope.cn/organization/01ai) β’ [π wisemodel](https://wisemodel.cn/organization/01.AI)|
|
36 |
+
| Yi-1.5-34B-Chat-16K | β’ [π€ Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) β’ [π€ ModelScope](https://www.modelscope.cn/organization/01ai) β’ [π wisemodel](https://wisemodel.cn/organization/01.AI)|
|
37 |
+
| Yi-1.5-9B-Chat | β’ [π€ Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) β’ [π€ ModelScope](https://www.modelscope.cn/organization/01ai) β’ [π wisemodel](https://wisemodel.cn/organization/01.AI)|
|
38 |
+
| Yi-1.5-9B-Chat-16K | β’ [π€ Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) β’ [π€ ModelScope](https://www.modelscope.cn/organization/01ai) β’ [π wisemodel](https://wisemodel.cn/organization/01.AI)|
|
39 |
+
| Yi-1.5-6B-Chat | β’ [π€ Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) β’ [π€ ModelScope](https://www.modelscope.cn/organization/01ai) β’ [π wisemodel](https://wisemodel.cn/organization/01.AI)|
|
40 |
+
|
41 |
+
</div>
|
42 |
+
|
43 |
+
- Base models
|
44 |
+
|
45 |
+
<div align="center">
|
46 |
+
|
47 |
+
| Name | Download |
|
48 |
+
| ---------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
49 |
+
| Yi-1.5-34B | β’ [π€ Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) β’ [π€ ModelScope](https://www.modelscope.cn/organization/01ai) β’ [π wisemodel](https://wisemodel.cn/organization/01.AI)|
|
50 |
+
| Yi-1.5-34B-32K | β’ [π€ Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) β’ [π€ ModelScope](https://www.modelscope.cn/organization/01ai) β’ [π wisemodel](https://wisemodel.cn/organization/01.AI)|
|
51 |
+
| Yi-1.5-9B | β’ [π€ Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) β’ [π€ ModelScope](https://www.modelscope.cn/organization/01ai) β’ [π wisemodel](https://wisemodel.cn/organization/01.AI)|
|
52 |
+
| Yi-1.5-9B-32K | β’ [π€ Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) β’ [π€ ModelScope](https://www.modelscope.cn/organization/01ai) β’ [π wisemodel](https://wisemodel.cn/organization/01.AI)|
|
53 |
+
| Yi-1.5-6B | β’ [π€ Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) β’ [π€ ModelScope](https://www.modelscope.cn/organization/01ai) β’ [π wisemodel](https://wisemodel.cn/organization/01.AI)|
|
54 |
+
|
55 |
+
</div>
|
56 |
+
|
57 |
+
# Benchmarks
|
58 |
+
|
59 |
+
- Chat models
|
60 |
+
|
61 |
+
Yi-1.5-34B-Chat is on par with or excels beyond larger models in most benchmarks.
|
62 |
+
|
63 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/656d9adce8bf55919aca7c3f/KcsJ9Oc1VnEmfCDEJc5cd.png)
|
64 |
+
|
65 |
+
Yi-1.5-9B-Chat is the top performer among similarly sized open-source models.
|
66 |
+
|
67 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/656d9adce8bf55919aca7c3f/xf6pLg5jqRCwjlh6m3t6_.png)
|
68 |
+
|
69 |
+
- Base models
|
70 |
+
|
71 |
+
Yi-1.5-34B is on par with or excels beyond larger models in some benchmarks.
|
72 |
+
|
73 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/656d9adce8bf55919aca7c3f/BwU7QM-03dZvZzwdIE1xY.png)
|
74 |
+
|
75 |
+
Yi-1.5-9B is the top performer among similarly sized open-source models.
|
76 |
+
|
77 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/656d9adce8bf55919aca7c3f/y-EYSYPT-3aWLJ0x8R94F.png)
|
78 |
+
|
79 |
+
# Quick Start
|
80 |
+
|
81 |
+
For getting up and running with Yi-1.5 models quickly, see [README](https://github.com/01-ai/Yi-1.5).
|