Commit
•
99b19ab
1
Parent(s):
26acde1
Update README.md
Browse files
README.md
CHANGED
|
@@ -10,7 +10,7 @@ tags:
|
|
| 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 |
|
| 15 |
<center><img src="k2_eval_table.png" alt="k2 eval table" width="450"/></center>
|
| 16 |
|
|
|
|
| 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. K2 is fully transparent, meaning we’ve open-sourced all artifacts, including code, data, model checkpoints, intermediate results, and more.
|
| 14 |
|
| 15 |
<center><img src="k2_eval_table.png" alt="k2 eval table" width="450"/></center>
|
| 16 |
|