Commit
•
76369b4
1
Parent(s):
01e756b
uploaded readme
Browse files
README.md
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Quantization made by Richard Erkhov.
|
| 2 |
+
|
| 3 |
+
[Github](https://github.com/RichardErkhov)
|
| 4 |
+
|
| 5 |
+
[Discord](https://discord.gg/pvy7H8DZMG)
|
| 6 |
+
|
| 7 |
+
[Request more models](https://github.com/RichardErkhov/quant_request)
|
| 8 |
+
|
| 9 |
+
|
| 10 |
+
Llama3.2-1B-summary-length-exp7 - AWQ
|
| 11 |
+
- Model creator: https://huggingface.co/amang1802/
|
| 12 |
+
- Original model: https://huggingface.co/amang1802/Llama3.2-1B-summary-length-exp7/
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
Original model description:
|
| 18 |
+
---
|
| 19 |
+
library_name: transformers
|
| 20 |
+
tags: []
|
| 21 |
+
---
|
| 22 |
+
|
| 23 |
+
# Model Card for Model ID
|
| 24 |
+
|
| 25 |
+
- Summary Length PPO experiment #7
|
| 26 |
+
- No KL divergence in loss
|
| 27 |
+
|
| 28 |
+
## Model Details
|
| 29 |
+
|
| 30 |
+
- Dataset size: 16384
|
| 31 |
+
- Epochs: 1
|
| 32 |
+
- Batch Size: 16 * 4 (w/ 4 GPUs)
|
| 33 |
+
|
| 34 |
+
Optimizer args: Torch AdamW default, except
|
| 35 |
+
- LR = 0.00001
|
| 36 |
+
|