Hugging Face's logo

RichardErkhov
/
01-ai_-_Yi-1.5-9B-gguf

GGUF
Model card Files
xet
 Community
RichardErkhov commited on
Commit
8d38beb
·
verified ·
1 Parent(s): 227f150

uploaded readme

Browse files
Files changed (1) hide show
  1. README.md +138 -0
README.md ADDED
@@ -0,0 +1,138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Quantization made by Richard Erkhov.
2
+
3
+ [Github](https://github.com/RichardErkhov)
4
+
5
+ [Discord](https://discord.gg/pvy7H8DZMG)
6
+
7
+ [Request more models](https://github.com/RichardErkhov/quant_request)
8
+
9
+
10
+ Yi-1.5-9B - GGUF
11
+ - Model creator: https://huggingface.co/01-ai/
12
+ - Original model: https://huggingface.co/01-ai/Yi-1.5-9B/
13
+
14
+
15
+ | Name | Quant method | Size |
16
+ | ---- | ---- | ---- |
17
+ | [Yi-1.5-9B.Q2_K.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-gguf/blob/main/Yi-1.5-9B.Q2_K.gguf) | Q2_K | 3.12GB |
18
+ | [Yi-1.5-9B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-gguf/blob/main/Yi-1.5-9B.IQ3_XS.gguf) | IQ3_XS | 3.46GB |
19
+ | [Yi-1.5-9B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-gguf/blob/main/Yi-1.5-9B.IQ3_S.gguf) | IQ3_S | 3.64GB |
20
+ | [Yi-1.5-9B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-gguf/blob/main/Yi-1.5-9B.Q3_K_S.gguf) | Q3_K_S | 3.63GB |
21
+ | [Yi-1.5-9B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-gguf/blob/main/Yi-1.5-9B.IQ3_M.gguf) | IQ3_M | 3.78GB |
22
+ | [Yi-1.5-9B.Q3_K.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-gguf/blob/main/Yi-1.5-9B.Q3_K.gguf) | Q3_K | 4.03GB |
23
+ | [Yi-1.5-9B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-gguf/blob/main/Yi-1.5-9B.Q3_K_M.gguf) | Q3_K_M | 4.03GB |
24
+ | [Yi-1.5-9B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-gguf/blob/main/Yi-1.5-9B.Q3_K_L.gguf) | Q3_K_L | 4.37GB |
25
+ | [Yi-1.5-9B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-gguf/blob/main/Yi-1.5-9B.IQ4_XS.gguf) | IQ4_XS | 4.5GB |
26
+ | [Yi-1.5-9B.Q4_0.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-gguf/blob/main/Yi-1.5-9B.Q4_0.gguf) | Q4_0 | 4.69GB |
27
+ | [Yi-1.5-9B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-gguf/blob/main/Yi-1.5-9B.IQ4_NL.gguf) | IQ4_NL | 4.73GB |
28
+ | [Yi-1.5-9B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-gguf/blob/main/Yi-1.5-9B.Q4_K_S.gguf) | Q4_K_S | 4.72GB |
29
+ | [Yi-1.5-9B.Q4_K.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-gguf/blob/main/Yi-1.5-9B.Q4_K.gguf) | Q4_K | 4.96GB |
30
+ | [Yi-1.5-9B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-gguf/blob/main/Yi-1.5-9B.Q4_K_M.gguf) | Q4_K_M | 4.96GB |
31
+ | [Yi-1.5-9B.Q4_1.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-gguf/blob/main/Yi-1.5-9B.Q4_1.gguf) | Q4_1 | 5.19GB |
32
+ | [Yi-1.5-9B.Q5_0.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-gguf/blob/main/Yi-1.5-9B.Q5_0.gguf) | Q5_0 | 5.69GB |
33
+ | [Yi-1.5-9B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-gguf/blob/main/Yi-1.5-9B.Q5_K_S.gguf) | Q5_K_S | 5.69GB |
34
+ | [Yi-1.5-9B.Q5_K.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-gguf/blob/main/Yi-1.5-9B.Q5_K.gguf) | Q5_K | 5.83GB |
35
+ | [Yi-1.5-9B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-gguf/blob/main/Yi-1.5-9B.Q5_K_M.gguf) | Q5_K_M | 5.83GB |
36
+ | [Yi-1.5-9B.Q5_1.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-gguf/blob/main/Yi-1.5-9B.Q5_1.gguf) | Q5_1 | 6.19GB |
37
+ | [Yi-1.5-9B.Q6_K.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-gguf/blob/main/Yi-1.5-9B.Q6_K.gguf) | Q6_K | 6.75GB |
38
+ | [Yi-1.5-9B.Q8_0.gguf](https://huggingface.co/RichardErkhov/01-ai_-_Yi-1.5-9B-gguf/blob/main/Yi-1.5-9B.Q8_0.gguf) | Q8_0 | 8.74GB |
39
+
40
+
41
+
42
+
43
+ Original model description:
44
+ ---
45
+ license: apache-2.0
46
+ ---
47
+ <div align="center">
48
+
49
+ <picture>
50
+ <img src="https://raw.githubusercontent.com/01-ai/Yi/main/assets/img/Yi_logo_icon_light.svg" width="150px">
51
+ </picture>
52
+
53
+ </div>
54
+
55
+ <p align="center">
56
+ <a href="https://github.com/01-ai">🐙 GitHub</a> •
57
+ <a href="https://discord.gg/hYUwWddeAu">👾 Discord</a> •
58
+ <a href="https://twitter.com/01ai_yi">🐤 Twitter</a> •
59
+ <a href="https://github.com/01-ai/Yi-1.5/issues/2">💬 WeChat</a>
60
+ <br/>
61
+ <a href="https://arxiv.org/abs/2403.04652">📝 Paper</a> •
62
+ <a href="https://01-ai.github.io/">💪 Tech Blog</a> •
63
+ <a href="https://github.com/01-ai/Yi/tree/main?tab=readme-ov-file#faq">🙌 FAQ</a> •
64
+ <a href="https://github.com/01-ai/Yi/tree/main?tab=readme-ov-file#learning-hub">📗 Learning Hub</a>
65
+ </p>
66
+
67
+ # Intro
68
+
69
+ 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.
70
+
71
+ 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.
72
+
73
+ <div align="center">
74
+
75
+ Model | Context Length | Pre-trained Tokens
76
+ | :------------: | :------------: | :------------: |
77
+ | Yi-1.5 | 4K, 16K, 32K | 3.6T
78
+
79
+ </div>
80
+
81
+ # Models
82
+
83
+ - Chat models
84
+
85
+ <div align="center">
86
+
87
+ | Name | Download |
88
+ | --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
89
+ | Yi-1.5-34B-Chat | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) • [🟣 wisemodel](https://wisemodel.cn/organization/01.AI)|
90
+ | Yi-1.5-34B-Chat-16K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) • [🟣 wisemodel](https://wisemodel.cn/organization/01.AI) |
91
+ | Yi-1.5-9B-Chat | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) • [🟣 wisemodel](https://wisemodel.cn/organization/01.AI) |
92
+ | Yi-1.5-9B-Chat-16K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) • [🟣 wisemodel](https://wisemodel.cn/organization/01.AI) |
93
+ | Yi-1.5-6B-Chat | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) • [🟣 wisemodel](https://wisemodel.cn/organization/01.AI) |
94
+
95
+ </div>
96
+
97
+ - Base models
98
+
99
+ <div align="center">
100
+
101
+ | Name | Download |
102
+ | ---------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
103
+ | Yi-1.5-34B | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) • [🟣 wisemodel](https://wisemodel.cn/organization/01.AI) |
104
+ | Yi-1.5-34B-32K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) • [🟣 wisemodel](https://wisemodel.cn/organization/01.AI) |
105
+ | Yi-1.5-9B | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) • [🟣 wisemodel](https://wisemodel.cn/organization/01.AI) |
106
+ | Yi-1.5-9B-32K | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) • [🟣 wisemodel](https://wisemodel.cn/organization/01.AI) |
107
+ | Yi-1.5-6B | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) • [🟣 wisemodel](https://wisemodel.cn/organization/01.AI) |
108
+
109
+ </div>
110
+
111
+ # Benchmarks
112
+
113
+ - Chat models
114
+
115
+ Yi-1.5-34B-Chat is on par with or excels beyond larger models in most benchmarks.
116
+
117
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/656d9adce8bf55919aca7c3f/KcsJ9Oc1VnEmfCDEJc5cd.png)
118
+
119
+ Yi-1.5-9B-Chat is the top performer among similarly sized open-source models.
120
+
121
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/656d9adce8bf55919aca7c3f/xf6pLg5jqRCwjlh6m3t6_.png)
122
+
123
+ - Base models
124
+
125
+ Yi-1.5-34B is on par with or excels beyond larger models in some benchmarks.
126
+
127
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/656d9adce8bf55919aca7c3f/BwU7QM-03dZvZzwdIE1xY.png)
128
+
129
+ Yi-1.5-9B is the top performer among similarly sized open-source models.
130
+
131
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/656d9adce8bf55919aca7c3f/y-EYSYPT-3aWLJ0x8R94F.png)
132
+
133
+ # Quick Start
134
+
135
+ For getting up and running with Yi-1.5 models quickly, see [README](https://github.com/01-ai/Yi-1.5).
136
+
137
+
138
+