Upload README.md with huggingface_hub
Browse files
README.md
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
pipeline_tag: text-generation
|
6 |
+
inference: false
|
7 |
+
tags:
|
8 |
+
- transformers
|
9 |
+
- gguf
|
10 |
+
- imatrix
|
11 |
+
- chronos-13b-v2
|
12 |
+
---
|
13 |
+
Quantizations of https://huggingface.co/elinas/chronos-13b-v2
|
14 |
+
|
15 |
+
|
16 |
+
# From original readme
|
17 |
+
|
18 |
+
This is the FP16 PyTorch / HF version of **chronos-13b-v2** based on the **LLaMA v2 Base** model.
|
19 |
+
|
20 |
+
Only use this version for further quantization or if you would like to run in full precision, as long as you have the VRAM required.
|
21 |
+
|
22 |
+
This model is primarily focused on chat, roleplay, storywriting, with good reasoning and logic.
|
23 |
+
|
24 |
+
Chronos can generate very long outputs with coherent text, largely due to the human inputs it was trained on, and it supports context length up to 4096 tokens.
|
25 |
+
|
26 |
+
This model uses Alpaca formatting, so for optimal model performance, use it to start the dialogue or story, and if you use a frontend like SillyTavern ENABLE instruction mode:
|
27 |
+
```
|
28 |
+
### Instruction:
|
29 |
+
Your instruction or question here.
|
30 |
+
### Response:
|
31 |
+
```
|
32 |
+
Not using the format will make the model perform significantly worse than intended.
|