Update README.md
Browse files
README.md
CHANGED
@@ -1,22 +1,27 @@
|
|
1 |
---
|
2 |
language:
|
3 |
- en
|
4 |
-
license:
|
5 |
tags:
|
6 |
- text-generation-inference
|
7 |
- transformers
|
8 |
- unsloth
|
9 |
- mistral
|
10 |
-
-
|
11 |
base_model: ammarali32/multi_verse_model
|
|
|
|
|
12 |
---
|
13 |
|
14 |
-
#
|
15 |
|
16 |
- **Developed by:** maldv
|
17 |
-
- **License:**
|
18 |
-
- **Finetuned from model
|
|
|
19 |
|
20 |
-
|
21 |
|
22 |
-
|
|
|
|
|
|
1 |
---
|
2 |
language:
|
3 |
- en
|
4 |
+
license: cc-by-nc-4.0
|
5 |
tags:
|
6 |
- text-generation-inference
|
7 |
- transformers
|
8 |
- unsloth
|
9 |
- mistral
|
10 |
+
- GEB
|
11 |
base_model: ammarali32/multi_verse_model
|
12 |
+
datasets:
|
13 |
+
- maldv/crabcanon
|
14 |
---
|
15 |
|
16 |
+
# SHRDFU-7b Δ
|
17 |
|
18 |
- **Developed by:** maldv
|
19 |
+
- **License:** cc-by-nc-4.0
|
20 |
+
- **Finetuned from model:** ammarali32/multi_verse_model
|
21 |
+
- **Methodology:** Peft to train; extending intelligence and problem solving w/ crabcanon
|
22 |
|
23 |
+
As I work on understanding how to layer information in to the model, this model used no conditioning and even with low LR's, had quite a sharp graph. It definitely inherited the style of the source.
|
24 |
|
25 |
+
I had been experimenting in this series with wrapping each paragraph or turn with `<s></s>` bos/eos tokens. This may be semi-compatible with instruct, but is incompatible with alpaca and chatml. Good to know.
|
26 |
+
|
27 |
+
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="50"/>](https://github.com/unslothai/unsloth)
|