Commit
•
f6ecceb
1
Parent(s):
5557fe7
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# Reflection 70B
|
| 2 |
|
| 3 |
**Reflection 70B is (currently) the world's top open-source LLM, trained with a new technique called Reflection-Tuning that teaches a LLM to detect mistakes in its reasoning and correct course.**
|
|
@@ -50,9 +54,4 @@ Both the dataset and a brief report detailing how we trained this model will be
|
|
| 50 |
|
| 51 |
---
|
| 52 |
|
| 53 |
-
Thanks to Jason Kuperberg and Josh Bickett from the [HyperWrite](https://hyperwriteai.com) team for reviewing drafts of the report we'll be releasing next week.
|
| 54 |
-
|
| 55 |
-
---
|
| 56 |
-
license: llama3.1
|
| 57 |
-
base_model: meta-llama/Meta-Llama-3.1-70B-Instruct
|
| 58 |
-
---
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama3.1
|
| 3 |
+
base_model: meta-llama/Meta-Llama-3.1-70B-Instruct
|
| 4 |
+
---
|
| 5 |
# Reflection 70B
|
| 6 |
|
| 7 |
**Reflection 70B is (currently) the world's top open-source LLM, trained with a new technique called Reflection-Tuning that teaches a LLM to detect mistakes in its reasoning and correct course.**
|
|
|
|
| 54 |
|
| 55 |
---
|
| 56 |
|
| 57 |
+
Thanks to Jason Kuperberg and Josh Bickett from the [HyperWrite](https://hyperwriteai.com) team for reviewing drafts of the report we'll be releasing next week.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|