Update README.md
Browse files
README.md
CHANGED
|
@@ -13,7 +13,7 @@ base_model: tiiuae/falcon-180B
|
|
| 13 |
|
| 14 |
# falcon-180b-instruct-peft 🦅
|
| 15 |
|
| 16 |
-
This instruction model was built via parameter-efficient QLoRA finetuning of [falcon-180b](https://huggingface.co/tiiuae/falcon-180B) on the first 5k rows of [ehartford/dolphin](https://huggingface.co/datasets/ehartford/dolphin) and the first 5k
|
| 17 |
|
| 18 |
### Benchmark metrics
|
| 19 |
|
|
|
|
| 13 |
|
| 14 |
# falcon-180b-instruct-peft 🦅
|
| 15 |
|
| 16 |
+
This instruction model was built via parameter-efficient QLoRA finetuning of [falcon-180b](https://huggingface.co/tiiuae/falcon-180B) on the first 5k rows of [ehartford/dolphin](https://huggingface.co/datasets/ehartford/dolphin) and the first 5k rows of [garage-bAInd/Open-Platypus](https://huggingface.co/datasets/garage-bAInd/Open-Platypus). Finetuning was executed on 4x A6000s (48 GB RTX) for roughly 32 hours on the [Lambda Labs](https://cloud.lambdalabs.com/instances) platform.
|
| 17 |
|
| 18 |
### Benchmark metrics
|
| 19 |
|