File size: 469 Bytes
5d7fb6e
 
 
4de44e5
5d7fb6e
 
 
 
 
 
 
4de44e5
5d7fb6e
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
Lora fine tune trained on this [dataset](https://huggingface.co/datasets/ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered) 


```python
Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{data_point["instruction"]}

### Response:
{data_point["output"]}
```

CUDA_VISIBLE_DEVICES=0
python llama.py model c4 --wbits 4 --true-sequential --groupsize 128 --save_safetensors 4bit-128g.safetensors