Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama2
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
GGUF Quants.
|
| 8 |
+
<br>For fp16 Repo, visit: https://huggingface.co/Sao10K/Hesperus-v1-13B-L2
|
| 9 |
+
<br>For Adapter, visit: https://huggingface.co/Sao10K/Hesperus-v1-LoRA
|
| 10 |
+
|
| 11 |
+
Hesperus-v1 - A trained 8-bit LoRA for RP & General Purposes.
|
| 12 |
+
<br>Trained on the base 13B Llama 2 model.
|
| 13 |
+
|
| 14 |
+
Dataset Entry Rows:
|
| 15 |
+
<br>RP: 8.95K
|
| 16 |
+
<br>MED: 10.5K
|
| 17 |
+
<br>General: 8.7K
|
| 18 |
+
<br>Total: 28.15K
|
| 19 |
+
|
| 20 |
+
This is after heavy filtering of ~500K Rows and Entries.
|
| 21 |
+
<br> V2 will see this further reduced down to ~10K after I do a second round of cleaning.
|
| 22 |
+
|
| 23 |
+
Applicable Formats:
|
| 24 |
+
|
| 25 |
+
ShareGPT / Vicuna
|
| 26 |
+
<br>Alpaca
|
| 27 |
+
|
| 28 |
+
V1 is trained on 50/50 for these two formats.
|
| 29 |
+
<br>I am working on converting to either for v2.
|
| 30 |
+
|
| 31 |
+
Once V2 is Completed, I will also train a 70B variant of this.
|
| 32 |
+
|
| 33 |
+
***
|
| 34 |
+
|
| 35 |
+
This model was trained from scratch on the Hesperus dataset.
|
| 36 |
+
It achieves the following results on the evaluation set:
|
| 37 |
+
- Loss: 1.5134
|
| 38 |
+
|
| 39 |
+
- ***
|
| 40 |
+
|
| 41 |
+
<br>
|