Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,26 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
license_link: https://huggingface.co/rhysjones/Phi-3-mini-mango-1-llamafied/resolve/main/LICENSE
|
| 4 |
+
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
pipeline_tag: text-generation
|
| 8 |
+
tags:
|
| 9 |
+
- nlp
|
| 10 |
+
- code
|
| 11 |
+
widget:
|
| 12 |
+
- messages:
|
| 13 |
+
- role: user
|
| 14 |
+
content: Can you provide ways to eat combinations of bananas and dragonfruits?
|
| 15 |
---
|
| 16 |
+
|
| 17 |
+
## Model Summary
|
| 18 |
+
|
| 19 |
+
The Phi-3-mini-mango-1-llamafied is an instruct finetune of [Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) with 4K context and 3.8B parameters.
|
| 20 |
+
|
| 21 |
+
It is a first cut of finetuning Phi-3 to explore its properties and behaviour. More to follow!
|
| 22 |
+
|
| 23 |
+
This version of the model has had its weight layers converted to Llama format so that it can be used without trust_remote_code = true.
|
| 24 |
+
The Phi-3 format model will be uploaded once transformers-40.0.0.dev0 is released to stable.
|
| 25 |
+
|
| 26 |
+
|