Commit
·
bdca489
1
Parent(s):
debb252
Update README.md
Browse files
README.md
CHANGED
|
@@ -7,7 +7,6 @@ sdk: static
|
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
-
|
| 11 |
|
| 12 |
|
| 13 |
# Introducing Lamini, the LLM Engine for Rapid Customization
|
|
@@ -18,6 +17,7 @@ Today, you can try out our open dataset generator for training instruction-follo
|
|
| 18 |
|
| 19 |
[Sign up](https://lamini.ai/contact) for early access to our full LLM training module, including enterprise features like cloud prem deployments.
|
| 20 |
|
|
|
|
| 21 |
|
| 22 |
# Training LLMs should be as easy as prompt-tuning 🦾
|
| 23 |
Why is writing a prompt so easy, but training an LLM from a base model still so hard? Iteration cycles for finetuning on modest datasets are measured in months because it takes significant time to figure out why finetuned models fail. Conversely, prompt-tuning iterations are on the order of seconds, but performance plateaus in a matter of hours. Only a limited amount of data can be crammed into the prompt, not the terabytes of data in a warehouse.
|
|
|
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
|
|
|
| 10 |
|
| 11 |
|
| 12 |
# Introducing Lamini, the LLM Engine for Rapid Customization
|
|
|
|
| 17 |
|
| 18 |
[Sign up](https://lamini.ai/contact) for early access to our full LLM training module, including enterprise features like cloud prem deployments.
|
| 19 |
|
| 20 |
+
|
| 21 |
|
| 22 |
# Training LLMs should be as easy as prompt-tuning 🦾
|
| 23 |
Why is writing a prompt so easy, but training an LLM from a base model still so hard? Iteration cycles for finetuning on modest datasets are measured in months because it takes significant time to figure out why finetuned models fail. Conversely, prompt-tuning iterations are on the order of seconds, but performance plateaus in a matter of hours. Only a limited amount of data can be crammed into the prompt, not the terabytes of data in a warehouse.
|