Commit
•
16e4067
1
Parent(s):
a1756d9
Update README.md
Browse files
README.md
CHANGED
|
@@ -3,6 +3,10 @@ license: llama3.1
|
|
| 3 |
base_model: meta-llama/Meta-Llama-3.1-70B-Instruct
|
| 4 |
pipeline_tag: text-generation
|
| 5 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
# Reflection Llama-3.1 70B
|
| 7 |
|
| 8 |
**Reflection Llama-3.1 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.**
|
|
|
|
| 3 |
base_model: meta-llama/Meta-Llama-3.1-70B-Instruct
|
| 4 |
pipeline_tag: text-generation
|
| 5 |
---
|
| 6 |
+
|
| 7 |
+
This is the BF16 version converted from BF32 of the original model [mattshumer/Reflection-Llama-3.1-70B](https://huggingface.co/mattshumer/Reflection-Llama-3.1-70B)
|
| 8 |
+
|
| 9 |
+
|
| 10 |
# Reflection Llama-3.1 70B
|
| 11 |
|
| 12 |
**Reflection Llama-3.1 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.**
|