初始化项目,由ModelHub XC社区提供模型
Model: KnutJaegersberg/deacon-3b Source: Original Platform
This commit is contained in:
29
README.md
Normal file
29
README.md
Normal file
@@ -0,0 +1,29 @@
|
||||
---
|
||||
license: cc-by-nc-4.0
|
||||
datasets:
|
||||
- KnutJaegersberg/trilobite
|
||||
---
|
||||
|
||||
|
||||

|
||||
|
||||
|
||||
This model was fine tuned on AI filtered subsets of GPT-4 based subset of the Dolphin dataset and EvolInstruct V2.
|
||||
It has not been explicitly aligned to positive, negative or bureaucratically prescribed value systems.
|
||||
It might kill us all! Time to shit your pants, regulators. I literally put black goo on Dolphin-7B sperm, which then fertilized Evolved Instructions...
|
||||
What's different is evil... ;)
|
||||
I intend to train 3 sizes.
|
||||
|
||||
Prompt Example:
|
||||
```
|
||||
### System:
|
||||
|
||||
You are an AI assistant. User will give you a task. Your goal is to complete the task as faithfully as you can. While performing the task think step-by-step and justify your steps.
|
||||
|
||||
|
||||
### Instruction:
|
||||
|
||||
How do you fine tune a large language model?
|
||||
|
||||
### Response:
|
||||
```
|
||||
Reference in New Issue
Block a user