Update README.md
Browse files
README.md
CHANGED
|
@@ -150,7 +150,6 @@ During training, we truncate the input sequence to 2048 tokens, and for input se
|
|
| 150 |
## Infrastructure
|
| 151 |
|
| 152 |
We used [the Together Research Computer](https://together.xyz/) to conduct training.
|
| 153 |
-
The model was trained on computers networked with 1Gbps interconnect (in contrast, data center networks are 100Gbps-1.6Tbps).
|
| 154 |
|
| 155 |
# References
|
| 156 |
|
|
|
|
| 150 |
## Infrastructure
|
| 151 |
|
| 152 |
We used [the Together Research Computer](https://together.xyz/) to conduct training.
|
|
|
|
| 153 |
|
| 154 |
# References
|
| 155 |
|