48 lines
1.5 KiB
Markdown
48 lines
1.5 KiB
Markdown
---
|
|
license: apache-2.0
|
|
language:
|
|
- en
|
|
- th
|
|
library_name: transformers
|
|
pipeline_tag: text-generation
|
|
datasets:
|
|
- wannaphong/KhanomTanLLM-pretrained-dataset
|
|
---
|
|
# KhanomTan LLM (1B)
|
|
|
|
KhanomTan LLM is a bilingual language model trained in Thai and English from open source dataset by PyThaiNLP. We train the model from public dataset only. We public the dataset, source code, and model.
|
|
|
|
|
|
Repository: https://github.com/pythainlp/KhanomTanLLM
|
|
|
|
|
|
Codename: numfa-v2
|
|
|
|
## Model Details
|
|
|
|
### Model Description
|
|
|
|
The model was trained by [easylm](https://github.com/young-geng/EasyLM)
|
|
|
|
## Acknowledgements
|
|
|
|
Research supported with Cloud TPUs from Google's [TPU Research Cloud](https://sites.research.google/trc/about/) (TRC). We use TPU4-64 for training model about 4 days.
|
|
|
|
Thank you [TPU Research Cloud](https://sites.research.google/trc/about/) and [EasyLM project](https://github.com/young-geng/EasyLM)! We use EasyLM for pretraining model.
|
|
|
|
## How to use
|
|
|
|
**Example**
|
|
|
|
```python
|
|
# !pip install accelerate sentencepiece transformers bitsandbytes
|
|
import torch
|
|
from transformers import pipeline
|
|
|
|
pipe = pipeline("text-generation", model="numfa/numfa_v2-1b", torch_dtype=torch.bfloat16, device_map="auto")
|
|
|
|
# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
|
|
|
|
outputs = pipe("test is", max_new_tokens=300, do_sample=True, temperature=0.9, top_k=50, top_p=0.95, no_repeat_ngram_size=2,typical_p=1.)
|
|
print(outputs[0]["generated_text"])
|
|
``` |