|
|
--- |
|
|
base_model: TheBloke/Llama-2-7B-fp16 |
|
|
tags: |
|
|
- LoRA |
|
|
- bittensor |
|
|
- gradients |
|
|
license: apache-2.0 |
|
|
--- |
|
|
|
|
|
# Submission InstructionTask (LoRA) |
|
|
|
|
|
Fine-tuned on 2500 examples using Alpaca-like dataset with LoRA (r=16) on GPU. |
|
|
|
|
|
- **SHA256**: `8635187ed87214f676aa2d7ef67488d7950e2aeea0b8d679b0df84ca7b921326` |
|
|
- **Training**: 1 epoch, batch size 1, 4-bit quantization |
|
|
- **Upload time**: 2025-07-18T21:48:06+02:00 |
|
|
|
|
|
## Usage |
|
|
|
|
|
```python |
|
|
from peft import PeftModel |
|
|
from transformers import AutoModelForCausalLM |
|
|
|
|
|
base = AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-7B-fp16") |
|
|
model = PeftModel.from_pretrained(base, "raniero/submission_instruction_5000_gpu") |
|
|
``` |
|
|
|
