back

SCB 10X · 3.2B · Dense

Thai/English bilingual chat model built on Llama 3.2

0 downloads 0 likes 2024-12 88K context

Use Cases

chat multilingual

Quantization Options

Quant Bits VRAM Quality Status
Q2_K 2 1.5 GB low
Q3_K_M 3 1.9 GB moderate
Q4_K_M 4 2.1 GB good
Q5_K_M 5 2.5 GB good
Q6_K 6 3 GB excellent
Q8_0 8 3.8 GB excellent
F16 16 7.1 GB lossless

About this model

Llama3.2-Typhoon2-3B: Thai Large Language Model (Instruct) - Q4_K_M quantized

Llama3.2-Typhoon2-3B-instruct is a instruct Thai 🇹🇭 large language model with 3 billion parameters, and it is based on Llama3.2-3B.

By using this model, you agree to the OpenTyphoon Terms and Conditions and acknowledge the Privacy Notice: https://opentyphoon.ai/tac · https://opentyphoon.ai/privacy

*To acknowledge Meta’s effort in creating the foundation model and to comply with the license, we explicitly include “llama-3.2” in the model name.

Run

ollama run scb10x/llama3.2-typhoon2-3b-instruct

Performance

Instruction-Following & Function Call Performance

Typhoon General Performance

Detail Performance

Model IFEval - TH IFEval - EN MT-Bench TH MT-Bench EN Thai Code-Switching (t=0.7) Thai Code-Switching (t=1.0) FunctionCall-TH FunctionCall-EN
Typhoon2 Llama3.2 3B Instruct 68.36% 72.18% 5.3352 7.206 99.2% 96% 71.36% 75.90%
Qwen2.5 3B Instruct 58.86% 67.25% 4.6263 7.846 78.6% 38% 53.78% 62.55%
Llama3.2 3B Instruct 44.84% 71.98% 4.3241 7.725 93.8% 21.2% 35.43% 53.87%

Link

Arxiv

Huggingface