Commit
·
825f454
1
Parent(s):
44748e3
Update README.md
Browse files
README.md
CHANGED
|
@@ -12,6 +12,8 @@ Introducing EverythingLM, a llama-2 based, general-purpose 13b model with 16k co
|
|
| 12 |
|
| 13 |
The model is completely uncensored.
|
| 14 |
|
|
|
|
|
|
|
| 15 |
### Notable features:
|
| 16 |
- Automatically triggered CoT reasoning
|
| 17 |
- Verbose and detailed replies
|
|
@@ -29,8 +31,6 @@ ASSISTANT:
|
|
| 29 |
|
| 30 |
Training took about 1 hour using QLoRa on 1xA100, so this model can be recreated for about $3. QLoRa model can be found here: https://huggingface.co/totally-not-an-llm/EverythingLM-13b-peft.
|
| 31 |
|
| 32 |
-
This is an early test, so here are some things to note on the model:
|
| 33 |
-
|
| 34 |
### Model quirks:
|
| 35 |
- Due to the nature of the dataset, it does better with more detail. I've found it gives much better stories when I provide more requirements
|
| 36 |
- It really likes to use numbered lists. I don't necessarilly have a problem with this but it's something to note when training on the dataset
|
|
|
|
| 12 |
|
| 13 |
The model is completely uncensored.
|
| 14 |
|
| 15 |
+
This model is an early test of the EverythingLM dataset and some new experimental principles, so don't consider it SOTA.
|
| 16 |
+
|
| 17 |
### Notable features:
|
| 18 |
- Automatically triggered CoT reasoning
|
| 19 |
- Verbose and detailed replies
|
|
|
|
| 31 |
|
| 32 |
Training took about 1 hour using QLoRa on 1xA100, so this model can be recreated for about $3. QLoRa model can be found here: https://huggingface.co/totally-not-an-llm/EverythingLM-13b-peft.
|
| 33 |
|
|
|
|
|
|
|
| 34 |
### Model quirks:
|
| 35 |
- Due to the nature of the dataset, it does better with more detail. I've found it gives much better stories when I provide more requirements
|
| 36 |
- It really likes to use numbered lists. I don't necessarilly have a problem with this but it's something to note when training on the dataset
|