yi-01-ai commited on
Commit
cde5a0e
1 Parent(s): 4e005f8

Auto Sync from git://github.com/01-ai/Yi.git/commit/57b9e9f4e777740875aae331382d394997a97513

Browse files
Files changed (1) hide show
  1. README.md +7 -2
README.md CHANGED
@@ -133,7 +133,7 @@ pipeline_tag: text-generation
133
  >
134
  > The Yi series models adopt the same model architecture as Llama but are **NOT** derivatives of Llama.
135
 
136
- - Both Yi and Llama are all based on the Transformer structure, which has been the standard architecture for large language models since 2018.
137
 
138
  - Grounded in the Transformer architecture, Llama has become a new cornerstone for the majority of state-of-the-art open-source models due to its excellent stability, reliable convergence, and robust compatibility. This positions Llama as the recognized foundational framework for models including Yi.
139
 
@@ -153,10 +153,15 @@ pipeline_tag: text-generation
153
 
154
  ## News
155
 
 
 
 
 
 
156
  <details open>
157
  <summary>🔔 <b>2024-03-07</b>: The long text capability of the Yi-34B-200K has been enhanced. </summary>
158
  <br>
159
- In the "Needle-in-a-Haystack" test, the Yi-34B-200K's performance is improved by 10.5%, rising from 89.3% to an impressive 99.8%. We continue to pretrain the model on 5B tokens long-context data mixture and demonstrate a near-all-green performance.
160
  </details>
161
 
162
  <details open>
 
133
  >
134
  > The Yi series models adopt the same model architecture as Llama but are **NOT** derivatives of Llama.
135
 
136
+ - Both Yi and Llama are based on the Transformer structure, which has been the standard architecture for large language models since 2018.
137
 
138
  - Grounded in the Transformer architecture, Llama has become a new cornerstone for the majority of state-of-the-art open-source models due to its excellent stability, reliable convergence, and robust compatibility. This positions Llama as the recognized foundational framework for models including Yi.
139
 
 
153
 
154
  ## News
155
 
156
+ <details open>
157
+ <summary>🎯 <b>2024-03-08</b>: <a href="https://arxiv.org/abs/2403.04652">Yi Tech Report</a> is published! </summary>
158
+ </details>
159
+
160
+
161
  <details open>
162
  <summary>🔔 <b>2024-03-07</b>: The long text capability of the Yi-34B-200K has been enhanced. </summary>
163
  <br>
164
+ In the "Needle-in-a-Haystack" test, the Yi-34B-200K's performance is improved by 10.5%, rising from 89.3% to an impressive 99.8%. We continue to pre-train the model on 5B tokens long-context data mixture and demonstrate a near-all-green performance.
165
  </details>
166
 
167
  <details open>