eunyounglee/GPT-NeoX-1.3B-viet-final-GGUF

Quantized GGUF model files for GPT-NeoX-1.3B-viet-final from eunyounglee

Name	Quant method	Size
gpt-neox-1.3b-viet-final.q2_k.gguf	q2_k	635.16 MB
gpt-neox-1.3b-viet-final.q3_k_m.gguf	q3_k_m	789.55 MB
gpt-neox-1.3b-viet-final.q4_k_m.gguf	q4_k_m	944.92 MB
gpt-neox-1.3b-viet-final.q5_k_m.gguf	q5_k_m	1.09 GB
gpt-neox-1.3b-viet-final.q6_k.gguf	q6_k	1.20 GB
gpt-neox-1.3b-viet-final.q8_0.gguf	q8_0	1.55 GB

Original Model Card:

Model Card for Model ID

Pretrained GPT-NeoX model with 31.3 Vietnamese dataset. Took about 4.5 hours to reach 40,000 iterations. Trained on A100 40GB GPU and 48 core CPU.

Model Details

Model Description

• Developed by: Eunyoung Lee
• Model type: GPT-NeoX
• Language(s) (NLP): Vietnamese