Commit
•
f33d799
1
Parent(s):
8adb447
Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
|
| 4 |
+
license: cc-by-nc-4.0
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
# QuantFactory/MN-12B-Lyra-v4-GGUF
|
| 13 |
+
This is quantized version of [Sao10K/MN-12B-Lyra-v4](https://huggingface.co/Sao10K/MN-12B-Lyra-v4) created using llama.cpp
|
| 14 |
+
|
| 15 |
+
# Original Model Card
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
Mistral-NeMo-12B-Lyra-v4, a variation of [Lyra-v4a1](https://huggingface.co/Sao10K/MN-12B-Lyra-v4a1), layered over [Lyra-v3](https://huggingface.co/Sao10K/MN-12B-Lyra-v3), which was built on top of [Lyra-v2a2](https://huggingface.co/Sao10K/MN-12B-Lyra-v2a2), which itself was built upon [Lyra-v2a1](https://huggingface.co/Sao10K/MN-12B-Lyra-v2a1).
|
| 22 |
+
|
| 23 |
+
# Model Versioning
|
| 24 |
+
```
|
| 25 |
+
[See Previous Models]
|
| 26 |
+
|
|
| 27 |
+
Lyra-v4a1
|
| 28 |
+
|
|
| 29 |
+
------------> Lyra-v4 [Seperate RL Step targeting Instruct and Coherency over Base Nemo instead of SFT First, Result is Merged with Lyra-v4a1, fixes most quant-based issues. Somehow.]
|
| 30 |
+
```
|
| 31 |
+
|
| 32 |
+
# This uses ChatML, or any of its variants which were included in previous versions.
|
| 33 |
+
|
| 34 |
+
```
|
| 35 |
+
|
| 36 |
+
<|im_start|>system
|
| 37 |
+
This is the system prompt.<|im_end|>
|
| 38 |
+
<|im_start|>user
|
| 39 |
+
Instructions placed here.<|im_end|>
|
| 40 |
+
<|im_start|>assistant
|
| 41 |
+
The model's response will be here.<|im_end|>
|
| 42 |
+
--------------------------------------------------
|
| 43 |
+
[INST]system
|
| 44 |
+
This is another system prompt.[/INST]
|
| 45 |
+
[INST]user
|
| 46 |
+
Your instructions placed here.[/INST]
|
| 47 |
+
[INST]assistant
|
| 48 |
+
The model's response will be here.[/INST]
|
| 49 |
+
```
|
| 50 |
+
|
| 51 |
+
# Recommended Samplers:
|
| 52 |
+
|
| 53 |
+
```
|
| 54 |
+
Temperature: 0.6 - 1 # Make sure min_p is set before Temperature in Sampler Orders
|
| 55 |
+
min_p: 0.1 - 0.2 # Crucial for NeMo
|
| 56 |
+
```
|
| 57 |
+
|
| 58 |
+
# Recommended Stopping Strings:
|
| 59 |
+
|
| 60 |
+
```
|
| 61 |
+
<|im_end|>
|
| 62 |
+
</s>
|
| 63 |
+
[/INST]
|
| 64 |
+
```
|
| 65 |
+
|
| 66 |
+
# Notes
|
| 67 |
+
|
| 68 |
+
\- I think I fixed the extra token stuff some users seem to be facing, while retaining everything else? It's some error alright.
|
| 69 |
+
<br>\- If you're using XML tags, you may see weird malformed stopping strings. Just add them to your current list. and move on.
|
| 70 |
+
<br>\- Its pretty nice, imo. I've been messing around with it a lot.
|
| 71 |
+
<br>\- Make sure the ChatML template is correct, I think there's some issues with the one used in SillyTavern which might cause improper replies?
|