Update README.md
Browse files
README.md
CHANGED
|
@@ -13,6 +13,8 @@ Prompt format is standard chatml. Don't expect it to be good at math, riddles or
|
|
| 13 |
Cost of this fine-tune is about $10 in electricity. It took me 3 tries to get it right.
|
| 14 |
Base model used for fine-tuning was 200k context Yi-34B-Llama model shared by larryvrh.
|
| 15 |
|
|
|
|
|
|
|
| 16 |
|
| 17 |
## Prompt Format
|
| 18 |
|
|
|
|
| 13 |
Cost of this fine-tune is about $10 in electricity. It took me 3 tries to get it right.
|
| 14 |
Base model used for fine-tuning was 200k context Yi-34B-Llama model shared by larryvrh.
|
| 15 |
|
| 16 |
+
I had to change max_positional_embeddings in config.json and model_max_length to 4096 for training to start, otherwise I was OOMing straight away.
|
| 17 |
+
My first attempt had max_positional_embeddings set to 16384 and model_max_length set to 200000. This allowed fine-tuning to finish, but model was broken after applying LoRA and merging it.
|
| 18 |
|
| 19 |
## Prompt Format
|
| 20 |
|