Delta-Vector
commited on
Update README.md
Browse files
README.md
CHANGED
@@ -1,6 +1,8 @@
|
|
1 |
---
|
2 |
tags:
|
3 |
- chat
|
|
|
|
|
4 |
datasets:
|
5 |
- NewEden/OpenCAI-ShareGPT
|
6 |
- NewEden/vanilla-backrooms-claude-sharegpt
|
@@ -10,9 +12,11 @@ datasets:
|
|
10 |
Language:
|
11 |
- En
|
12 |
Pipeline_tag: text-generation
|
13 |
-
Base_model:
|
14 |
Tags:
|
15 |
- Chat
|
|
|
|
|
16 |
---
|
17 |
|
18 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/66c26b6fb01b19d8c3c2467b/7F2mX4Qqzmp8b0KG5i2DM.png)
|
@@ -22,7 +26,7 @@ A finetune of Mistral-Nemo-Instruct-2407 using conversational data, aiming for p
|
|
22 |
|
23 |
# Quants
|
24 |
|
25 |
-
GGUF:
|
26 |
|
27 |
EXL2 : https://huggingface.co/Delta-Vector/Ohashi-NeMo-12B-EXL2
|
28 |
|
@@ -257,4 +261,4 @@ The training was done for 4 epochs. We used 4 x [RTX 3090s](https://www.nvidia.
|
|
257 |
|
258 |
## Safety
|
259 |
|
260 |
-
![image/png](https://cdn-uploads.huggingface.co/production/uploads/66c26b6fb01b19d8c3c2467b/Wjgbdd-YjB56SCgrjdtL3.png)
|
|
|
1 |
---
|
2 |
tags:
|
3 |
- chat
|
4 |
+
- roleplay
|
5 |
+
- story-writing
|
6 |
datasets:
|
7 |
- NewEden/OpenCAI-ShareGPT
|
8 |
- NewEden/vanilla-backrooms-claude-sharegpt
|
|
|
12 |
Language:
|
13 |
- En
|
14 |
Pipeline_tag: text-generation
|
15 |
+
Base_model: mistralai/Mistral-Nemo-Instruct-2407
|
16 |
Tags:
|
17 |
- Chat
|
18 |
+
base_model:
|
19 |
+
- mistralai/Mistral-Nemo-Instruct-2407
|
20 |
---
|
21 |
|
22 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/66c26b6fb01b19d8c3c2467b/7F2mX4Qqzmp8b0KG5i2DM.png)
|
|
|
26 |
|
27 |
# Quants
|
28 |
|
29 |
+
GGUF: https://huggingface.co/Delta-Vector/Ohashi-NeMo-12B-gguf
|
30 |
|
31 |
EXL2 : https://huggingface.co/Delta-Vector/Ohashi-NeMo-12B-EXL2
|
32 |
|
|
|
261 |
|
262 |
## Safety
|
263 |
|
264 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/66c26b6fb01b19d8c3c2467b/Wjgbdd-YjB56SCgrjdtL3.png)
|