Update README.md
Browse files
README.md
CHANGED
|
@@ -8,7 +8,7 @@ tags:
|
|
| 8 |
- nlp
|
| 9 |
- llm
|
| 10 |
---
|
| 11 |
-
# K2: a
|
| 12 |
|
| 13 |
LLM360 demystifies the training recipe used for Llama 2 - 70B with K2.
|
| 14 |
|
|
|
|
| 8 |
- nlp
|
| 9 |
- llm
|
| 10 |
---
|
| 11 |
+
# K2: a fully-reproducible large language model outperforming Llama 2 70B using 35% less compute
|
| 12 |
|
| 13 |
LLM360 demystifies the training recipe used for Llama 2 - 70B with K2.
|
| 14 |
|