Pham commited on
Commit
89371f1
·
verified ·
1 Parent(s): db54e6d

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +36 -0
README.md ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: ms-pl
3
+ ---
4
+
5
+ ## Overview
6
+
7
+ The Phi-3, state-of-the-art open model trained with the Phi-3 datasets that includes both synthetic data and the filtered publicly available websites data with a focus on high-quality and reasoning dense properties. The model belongs to the Phi-3 family with the 4B, 7B version in two variants 8K and 128K which is the context length (in tokens) that it can support.
8
+
9
+ ## Variants
10
+
11
+ | No | Variant | Cortex CLI command |
12
+ | --- | --- | --- |
13
+ | 1 | [34B-gguf](https://huggingface.co/cortexhub/yi-1.5/tree/34B-gguf) | `cortex run yi-1.5:34B-gguf` |
14
+
15
+ ## Use it with Jan (UI)
16
+
17
+ 1. Install **Jan** using [Quickstart](https://jan.ai/docs/quickstart)
18
+ 2. Use in Jan model Hub:
19
+ ```
20
+ cortexhub/yi-1.5
21
+ ```
22
+
23
+ ## Use it with Cortex (CLI)
24
+
25
+ 1. Install **Cortex** using [Quickstart](https://cortex.jan.ai/docs/quickstart)
26
+ 2. Run the model with command:
27
+ ```
28
+ cortex run yi-1.5
29
+ ```
30
+
31
+ ## Credits
32
+
33
+ - **Author:** Microsoft
34
+ - **Converter:** [Homebrew](https://www.homebrew.ltd/)
35
+ - **Original License:** [Licence](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct/blob/main/LICENSE)
36
+ - **Papers:** [Phi-3 Technical Report](https://arxiv.org/abs/2404.14219)