yi-01-ai commited on
Commit
36326f9
1 Parent(s): f29622f

Auto Sync from git://github.com/01-ai/Yi.git/commit/e97d1e667e1de88793884becf33d0c2513bc3870

Browse files
Files changed (1) hide show
  1. README.md +50 -0
README.md CHANGED
@@ -73,6 +73,10 @@ pipeline_tag: text-generation
73
 
74
  - [🟢 What is Yi?](#-what-is-yi)
75
  - [📌 Introduction](#-introduction)
 
 
 
 
76
  - [🎉 News](#-news)
77
  - [🟢 Why Yi?](#-why-yi)
78
  - [🌎 Ecosystem](#-ecosystem)
@@ -105,6 +109,8 @@ pipeline_tag: text-generation
105
 
106
  </details>
107
 
 
 
108
  # 🟢 What is Yi?
109
 
110
  ## 📌 Introduction
@@ -121,6 +127,50 @@ pipeline_tag: text-generation
121
 
122
  <div align="right"> [ <a href="#building-the-next-generation-of-open-source-and-bilingual-llms">Back to top ⬆️ </a> ] </div>
123
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
124
  ## 🎉 News
125
 
126
  <details>
 
73
 
74
  - [🟢 What is Yi?](#-what-is-yi)
75
  - [📌 Introduction](#-introduction)
76
+ - [🎯 Models](#-models)
77
+ - [Chat models](#chat-models)
78
+ - [Base models](#base-models)
79
+ - [Other info](#other-info)
80
  - [🎉 News](#-news)
81
  - [🟢 Why Yi?](#-why-yi)
82
  - [🌎 Ecosystem](#-ecosystem)
 
109
 
110
  </details>
111
 
112
+ <hr>
113
+
114
  # 🟢 What is Yi?
115
 
116
  ## 📌 Introduction
 
127
 
128
  <div align="right"> [ <a href="#building-the-next-generation-of-open-source-and-bilingual-llms">Back to top ⬆️ </a> ] </div>
129
 
130
+ ## 🎯 Models
131
+
132
+ Yi models come in multiple sizes and cater to different use cases. You can also fine-tune Yi models to meet your specific requirements.
133
+
134
+ ### Chat models
135
+
136
+ | Model | Download
137
+ |---|---
138
+ Yi-6B-Chat| • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-6B-Chat) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-6B-Chat/summary)
139
+ Yi-6B-Chat-4bits | • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-6B-Chat-4bits) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-6B-Chat-4bits/summary)
140
+ Yi-6B-Chat-8bits | • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-6B-Chat-8bits) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-6B-Chat-8bits/summary)
141
+ Yi-34B-Chat | • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-34B-Chat) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-34B-Chat/summary)
142
+ Yi-34B-Chat-4bits | • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-34B-Chat-4bits) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-34B-Chat-4bits/summary)
143
+ Yi-34B-Chat-8bits | • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-34B-Chat-8bits) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-34B-Chat-8bits/summary)
144
+
145
+ <sub><sup> - 4 bits series models are quantized by AWQ. <br> - 8 bits series models are quantized by GPTQ <br> - All quantized models have a low barrier to use since they can be deployed on consumer-grade GPUs (e.g., 3090, 4090).</sup></sub>
146
+
147
+ ### Base models
148
+
149
+ | Model | Download |
150
+ |---|---|
151
+ Yi-6B| • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-6B) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-6B/summary)
152
+ Yi-6B-200K | • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-6B-200K) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-6B-200K/summary)
153
+ Yi-34B| • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-34B) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-34B/summary)
154
+ Yi-34B-200K|• [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-34B-200K) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-34B-200K/summary)
155
+
156
+ <sub><sup> - 200k is roughly equivalent to 400,000 Chinese characters. </sup></sub>
157
+
158
+ ### Other info
159
+
160
+ For chat models and base models:
161
+
162
+ - 6B series models are suitable for personal and academic use.
163
+
164
+ - 34B series models suitable for personal, academic, and commercial (particularly for small and medium-sized enterprises) purposes. It's a cost-effective solution that's affordable and equipped with emergent ability.
165
+
166
+ - The **default context window** is **4k tokens**.
167
+
168
+ - The pretrained tokens are 3T.
169
+
170
+ - The training data are up to June 2023.
171
+
172
+ <div align="right"> [ <a href="#building-the-next-generation-of-open-source-and-bilingual-llms">Back to top ⬆️ </a> ] </div>
173
+
174
  ## 🎉 News
175
 
176
  <details>