File size: 1,279 Bytes
d9cf33b d2eb966 d9cf33b 3cb4a20 d9cf33b 99a750a d2eb966 99a750a d2eb966 f5110dc 99a750a a86dd09 a123ed0 a86dd09 a123ed0 a86dd09 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 |
# Train
## Tokenizer
```bash
cd scripts
python -m venv venv
source venv/bin/activate
pip install -U -r requirements.in
```
```bash
python -B train_tokenizer.py
```
## Dataset
```bash
cd scripts
python -m venv venv-lit
source venv-lit/bin/activate
pip install -U -r requirements-lit.in
```
```bash
python -B prepare_pretrain_dataset.py
```
## Model
```bash
cd scripts
python -m venv venv-lit
source venv-lit/bin/activate
pip install -U -r requirements-lit.in
```
```bash
litgpt pretrain --config ./model.yaml
```
```bash
litgpt convert_from_litgpt out/pretrain/final/ out/converted_model
cp config.json out/pretrain/final/
cp config.json out/converted_model/
```
```python
import torch
from transformers import AutoModel
state_dict = torch.load('out/converted_model/model.pth')
model = AutoModel.from_pretrained('TinyLlama/TinyLlama_v1.1', state_dict=state_dict, ignore_mismatched_sizes=True)
model.save_pretrained('out/converted_model/')
```
## Evaluate
```bash
# litgpt evaluate --tasks 'hellaswag,gsm8k,truthfulqa_mc2,mmlu,winogrande,arc_challenge' --batch_size 8 out/pretrain/final/
litgpt evaluate --tasks 'hellaswag,gsm8k,truthfulqa_mc2,mmlu,mmlu_pro,winogrande,arc_challenge,leaderboard,ifeval,mgsm_direct,mathqa,gpqa' --batch_size 8 out/pretrain/final/
```
|