You can deploy this model and start earning money today!

RichardErkhov/
pythainlp_-_KhanomTanLLM-1B-gguf

Name: pythainlp_-_KhanomTanLLM-1B-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

KhanomTanLLM-1B - GGUF

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

Name	Quant method	Size
KhanomTanLLM-1B.Q2_K.gguf	Q2_K	0.55GB
KhanomTanLLM-1B.IQ3_XS.gguf	IQ3_XS	0.61GB
KhanomTanLLM-1B.IQ3_S.gguf	IQ3_S	0.63GB
KhanomTanLLM-1B.Q3_K_S.gguf	Q3_K_S	0.63GB
KhanomTanLLM-1B.IQ3_M.gguf	IQ3_M	0.66GB
KhanomTanLLM-1B.Q3_K.gguf	Q3_K	0.68GB
KhanomTanLLM-1B.Q3_K_M.gguf	Q3_K_M	0.68GB
KhanomTanLLM-1B.Q3_K_L.gguf	Q3_K_L	0.72GB
KhanomTanLLM-1B.IQ4_XS.gguf	IQ4_XS	0.73GB
KhanomTanLLM-1B.Q4_0.gguf	Q4_0	0.75GB
KhanomTanLLM-1B.IQ4_NL.gguf	IQ4_NL	0.76GB
KhanomTanLLM-1B.Q4_K_S.gguf	Q4_K_S	0.79GB
KhanomTanLLM-1B.Q4_K.gguf	Q4_K	0.83GB
KhanomTanLLM-1B.Q4_K_M.gguf	Q4_K_M	0.83GB
KhanomTanLLM-1B.Q4_1.gguf	Q4_1	0.83GB
KhanomTanLLM-1B.Q5_0.gguf	Q5_0	0.9GB
KhanomTanLLM-1B.Q5_K_S.gguf	Q5_K_S	0.91GB
KhanomTanLLM-1B.Q5_K.gguf	Q5_K	0.95GB
KhanomTanLLM-1B.Q5_K_M.gguf	Q5_K_M	0.95GB
KhanomTanLLM-1B.Q5_1.gguf	Q5_1	0.97GB
KhanomTanLLM-1B.Q6_K.gguf	Q6_K	1.11GB
KhanomTanLLM-1B.Q8_0.gguf	Q8_0	1.36GB

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

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"])

RichardErkhov/pythainlp_-_KhanomTanLLM-1B-gguf