|
--- |
|
language: |
|
- ms |
|
--- |
|
|
|
# Pretrain 3B 4096 context length Mistral on Malaysian text |
|
|
|
README at https://github.com/mesolitica/malaya/tree/5.1/pretrained-model/mistral |
|
|
|
- Dataset gathered at https://github.com/malaysia-ai/dedup-text-dataset/tree/main/pretrain-llm |
|
- We use Ray cluster to train on 5 nodes of 4x A100 80GB, https://github.com/malaysia-ai/jupyter-gpu/tree/main/ray |
|
|
|
WandB, https://wandb.ai/mesolitica/pretrain-mistral-3b?workspace=user-husein-mesolitica |
|
|
|
WandB report, https://wandb.ai/mesolitica/pretrain-mistral-3b/reports/Pretrain-Larger-Malaysian-Mistral--Vmlldzo2MDkyOTgz |
|
|
|
## how-to |
|
|
|
```python |
|
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig |
|
import torch |
|
|
|
TORCH_DTYPE = 'bfloat16' |
|
nf4_config = BitsAndBytesConfig( |
|
load_in_4bit=True, |
|
bnb_4bit_quant_type='nf4', |
|
bnb_4bit_use_double_quant=True, |
|
bnb_4bit_compute_dtype=getattr(torch, TORCH_DTYPE) |
|
) |
|
|
|
tokenizer = AutoTokenizer.from_pretrained('mesolitica/malaysian-mistral-3B-4096') |
|
model = AutoModelForCausalLM.from_pretrained( |
|
'mesolitica/malaysian-mistral-3B-4096', |
|
use_flash_attention_2 = True, |
|
quantization_config = nf4_config |
|
) |
|
prompt = '<s>nama saya' |
|
inputs = tokenizer([prompt], return_tensors='pt', add_special_tokens=False).to('cuda') |
|
|
|
generate_kwargs = dict( |
|
inputs, |
|
max_new_tokens=512, |
|
top_p=0.95, |
|
top_k=50, |
|
temperature=0.9, |
|
do_sample=True, |
|
num_beams=1, |
|
repetition_penalty=1.05, |
|
) |
|
r = model.generate(**generate_kwargs) |
|
``` |
