back

SCB 10X · 1.2B · Dense

Thai/English bilingual chat model for edge devices, built on Llama 3.2

0 downloads 0 likes 2024-12 88K context

Use Cases

chat multilingual edge

Quantization Options

Quant Bits VRAM Quality Status
Q2_K 2 0.9 GB low
Q3_K_M 3 1 GB moderate
Q4_K_M 4 1.1 GB good
Q5_K_M 5 1.3 GB good
Q6_K 6 1.4 GB excellent
Q8_0 8 1.7 GB excellent
F16 16 3 GB lossless

About this model

Llama3.2-Typhoon2-1B: Thai Large Language Model (Instruct) - Q4_K_M quantized

Llama3.2-Typhoon2-1B-instruct is a instruct Thai 🇹🇭 large language model with 1 billion parameters, and it is based on Llama3.2-1B.

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-typhoon2-1b-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 1b instruct 52.46% 53.35% 3.9725 5.2125 96.4% 88% 34.96% 45.60%
Qwen2.5 1.5b instruct 44.42% 48.45% 2.9395 6.9343 82.6% 20.6% 13.83% 17.88%
llama3.2 1b instruct 31.76% 51.15% 2.5824 6.229 97.8% 22.6% 29.88% 36.50%

Link

Arxiv

Huggingface