Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
inference: false
|
4 |
+
---
|
5 |
+
|
6 |
+
**NOTE: This "delta model" cannot be used directly.**
|
7 |
+
Users have to apply it on top of the original LLaMA weights.
|
8 |
+
See https://github.com/lm-sys/FastChat#vicuna-weights for instructions.
|
9 |
+
<br>
|
10 |
+
<br>
|
11 |
+
|
12 |
+
# scifi-fantasy-author Model Card
|
13 |
+
|
14 |
+
`scifi-fantasy-author` is a finetuned LLaMA model to generate narrative fiction,
|
15 |
+
paricularly in the Science Fiction and Fantasy genres.
|
16 |
+
|
17 |
+
The following hyperparameters were used
|
18 |
+
|Batch Size|Epochs|Context length|Learning rate|Scheduler|Weight decay|Warmup ratio|
|
19 |
+
|----------|------|--------------|-------------|---------|------------|------------|
|
20 |
+
| 64 | 3 | 8192 | 2e-5 | Cosine | 0. | 0.03 |
|
21 |
+
|
22 |
+
The model reached a training loss of 2.008 and took approximately 8 hours on 8x A100 80 GB GPUs.
|