Update README.md
Browse files
README.md
CHANGED
|
@@ -6,4 +6,12 @@ datasets:
|
|
| 6 |
- bigcode/starcoderdata
|
| 7 |
language:
|
| 8 |
- en
|
| 9 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
- bigcode/starcoderdata
|
| 7 |
language:
|
| 8 |
- en
|
| 9 |
+
---
|
| 10 |
+
Base model from PY007/TinyLlama-1.1B-intermediate-step-480k-1T
|
| 11 |
+
Fine tuned on OpenOrca GPT4 subset for 1 epoch.
|
| 12 |
+
Using CHATML format
|
| 13 |
+
Model License: Apache 2.0, following the TinyLlama base model.
|
| 14 |
+
|
| 15 |
+
Hardware and training spec:
|
| 16 |
+
Hardware: 1*RTX A5000, ~16 hours to complete 1 epoch. GPU from autodl.com, cost around $3 for this finetuning.
|
| 17 |
+
Training details:https://wandb.ai/jeff200402/TinyLlama-Orca?workspace=
|