Update README.md
Browse files
README.md
CHANGED
@@ -6,6 +6,24 @@ base_model:
|
|
6 |
- microsoft/Phi-3.5-mini-instruct
|
7 |
---
|
8 |
|
9 |
-
|
10 |
|
11 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
- microsoft/Phi-3.5-mini-instruct
|
7 |
---
|
8 |
|
9 |
+
# Phi-3.5 Mini-Instruct Modification using MedIT-mesh Technique
|
10 |
|
11 |
+
## Primary Use Cases:
|
12 |
+
|
13 |
+
- Commercial use in environments requiring memory and compute constraints.
|
14 |
+
- Use in latency-bound scenarios where accuracy is crucial.
|
15 |
+
- Strong reasoning capabilities, especially for code, math, and logic applications.
|
16 |
+
|
17 |
+
## Model Description:
|
18 |
+
The Phi-3.5 Mini-Instruct modification is designed to accelerate research on language and multimodal models. It is a 3.8B parameter model optimized for commercial and research use in multiple languages. The MedIT-mesh technique provides improved memory and compute efficiency, making it suitable for environments with limited resources.
|
19 |
+
|
20 |
+
## Use Case Considerations:
|
21 |
+
|
22 |
+
When selecting use cases, developers should consider language models' limitations and evaluate accuracy, safety, and fairness before using them within a specific downstream application.
|
23 |
+
Developers should be aware of applicable laws and regulations (e.g., privacy, trade compliance) relevant to their use case.
|
24 |
+
It is essential to adhere to the license terms for the model being used.
|
25 |
+
Release Notes:
|
26 |
+
|
27 |
+
An update over the June 2024 instruction-tuned Phi-3 Mini release based on user feedback.
|
28 |
+
Additional post-training data was incorporated, leading to substantial gains in multilingual and multi-turn conversation quality, and reasoning capability.
|
29 |
+
This release is expected to benefit most use cases, but users are encouraged to test in their particular AI applications.
|