45 lines
774 B
Markdown
45 lines
774 B
Markdown
---
|
|
license: mit
|
|
---
|
|
---
|
|
license: mit
|
|
---
|
|
|
|
Base Mode: Llama 7B
|
|
LoRA is fully Merged with llama7b, so you do not need to merge it to load the model.
|
|
|
|
Llama DEUS v3 is the largest dataset I've trained on yet, including:
|
|
|
|
GPTeacher - General Instruct - Code Instruct - Roleplay Instruct
|
|
My unreleased Roleplay V2 Instruct
|
|
GPT4-LLM Uncensored + Unnatural Instructions
|
|
WizardLM Uncensored
|
|
CamelAI's 20k Biology, 20k Physics, 20k Chemistry, and 50k Math GPT4 Datasets
|
|
CodeAlpaca
|
|
|
|
This model was trained for 4 epochs over 1 day of training, it's a rank 128 LORA that targets attention heads, LM_Head, and MLP layers
|
|
|
|
Prompt format:
|
|
|
|
```
|
|
### Instruction:
|
|
<prompt>
|
|
|
|
### Response:
|
|
|
|
```
|
|
|
|
or
|
|
|
|
```
|
|
### Instruction:
|
|
<prompt>
|
|
|
|
### Input:
|
|
<input>
|
|
|
|
### Response:
|
|
|
|
```
|
|
|