pythainlp_-_KhanomTanLLM-1B-awq

Quantization made by Richard Erkhov.

Github

Discord

Request more models

KhanomTanLLM-1B - AWQ

• Model creator: https://huggingface.co/pythainlp/
• Original model: https://huggingface.co/pythainlp/KhanomTanLLM-1B/

Original model description:

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

Acknowledgements

Research supported with Cloud TPUs from Google's TPU Research Cloud (TRC). We use TPU4-64 for training model about 4 days.

Thank you TPU Research Cloud and EasyLM project! We use EasyLM for pretraining model.

How to use

Example

# !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"])