Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
Open Hermes + Starling passthrough merged
|
| 2 |
|
| 3 |
SlimOrca(?)+Zephyr Beta linear merged, then passthrough merged with Synthia
|
|
@@ -14,4 +19,6 @@ Since most of the merged models were trained with ChatML, use ChatML template. R
|
|
| 14 |
- You can use some sort of CoT prompt instead of "system" in ChatML. It does improve the quality of most output.
|
| 15 |
(You are an assistant. Break down the question and come to a conclusion.)
|
| 16 |
|
| 17 |
-
I don't know what I am doing, you are very welcome to put the model through benchmarks.
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
---
|
| 6 |
Open Hermes + Starling passthrough merged
|
| 7 |
|
| 8 |
SlimOrca(?)+Zephyr Beta linear merged, then passthrough merged with Synthia
|
|
|
|
| 19 |
- You can use some sort of CoT prompt instead of "system" in ChatML. It does improve the quality of most output.
|
| 20 |
(You are an assistant. Break down the question and come to a conclusion.)
|
| 21 |
|
| 22 |
+
I don't know what I am doing, you are very welcome to put the model through benchmarks.
|
| 23 |
+
|
| 24 |
+
I'll also upload q6 GGUF but my internet is shit, so don't hesitate to share other quantizations.
|