You can deploy this model and start earning money today!

RichardErkhov/
pythainlp_-_KhanomTanLLM-3B-gguf

Name: pythainlp_-_KhanomTanLLM-3B-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

KhanomTanLLM-3B - GGUF

Model creator: https://huggingface.co/pythainlp/
Original model: https://huggingface.co/pythainlp/KhanomTanLLM-3B/

Name	Quant method	Size
KhanomTanLLM-3B.Q2_K.gguf	Q2_K	2.0GB
KhanomTanLLM-3B.IQ3_XS.gguf	IQ3_XS	2.0GB
KhanomTanLLM-3B.IQ3_S.gguf	IQ3_S	2.0GB
KhanomTanLLM-3B.Q3_K_S.gguf	Q3_K_S	2.0GB
KhanomTanLLM-3B.IQ3_M.gguf	IQ3_M	2.07GB
KhanomTanLLM-3B.Q3_K.gguf	Q3_K	2.15GB
KhanomTanLLM-3B.Q3_K_M.gguf	Q3_K_M	2.15GB
KhanomTanLLM-3B.Q3_K_L.gguf	Q3_K_L	2.22GB
KhanomTanLLM-3B.IQ4_XS.gguf	IQ4_XS	2.02GB
KhanomTanLLM-3B.Q4_0.gguf	Q4_0	2.0GB
KhanomTanLLM-3B.IQ4_NL.gguf	IQ4_NL	2.02GB
KhanomTanLLM-3B.Q4_K_S.gguf	Q4_K_S	2.41GB
KhanomTanLLM-3B.Q4_K.gguf	Q4_K	2.57GB
KhanomTanLLM-3B.Q4_K_M.gguf	Q4_K_M	2.57GB
KhanomTanLLM-3B.Q4_1.gguf	Q4_1	2.2GB
KhanomTanLLM-3B.Q5_0.gguf	Q5_0	2.4GB
KhanomTanLLM-3B.Q5_K_S.gguf	Q5_K_S	2.6GB
KhanomTanLLM-3B.Q5_K.gguf	Q5_K	2.74GB
KhanomTanLLM-3B.Q5_K_M.gguf	Q5_K_M	2.74GB
KhanomTanLLM-3B.Q5_1.gguf	Q5_1	2.6GB
KhanomTanLLM-3B.Q6_K.gguf	Q6_K	3.6GB
KhanomTanLLM-3B.Q8_0.gguf	Q8_0	3.6GB

Original model description:

license: apache-2.0 language:

en
th library_name: transformers datasets:
wannaphong/KhanomTanLLM-pretrained-dataset

KhanomTan LLM (3B)

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 8 days.

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

How to Get Started with the Model

Use the code below to get started with the model.

Example

python

# !pip install accelerate sentencepiece transformers bitsandbytes
import torch
from transformers import pipeline

pipe = pipeline("text-generation", model="numfa/numfa_v2-3b", 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"])

RichardErkhov/pythainlp_-_KhanomTanLLM-3B-gguf