scb10x/typhoon2.1-gemma3-4b

scb10x/ typhoon2.1-gemma3-4b:latest

23.5K Downloads Updated 1 year ago

Typhoon2.1 4B - 4B parameters Thai / English bilingual LLM build based on Gemma3.

tools

ollama run scb10x/typhoon2.1-gemma3-4b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "scb10x/typhoon2.1-gemma3-4b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='scb10x/typhoon2.1-gemma3-4b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'scb10x/typhoon2.1-gemma3-4b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 year ago

1 year ago

8cfab9097c9d · 2.6GB ·

model

archgemma3

parameters3.88B

quantizationQ4_K_M

2.6GB

template

{{- /* System message at the beginning, if there is .System or .Tools */ -}} {{- if or .System .Tool

2.2kB

system

You are a AI assistant named Typhoon created by SCB 10X to be helpful, harmless, and honest.

92B

license

Gemma Terms of Use Last modified: February 21, 2024 By using, reproducing, modifying, distributing,

8.4kB

params

{ "stop": [ "<end_of_turn>" ], "temperature": 0.6, "top_k": 64, "top_p":

79B

Readme

Typhoon2.1-Gemma3-4B: Thai Large Language Model (Instruct)

Typhoon2.1-Gemma3-4B is a instruct Thai 🇹🇭 large language model with 4 billion parameters, and it is based on Gemma3 4B.

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

Remark: This is text only model.

Run

ollama run scb10x/typhoon2.1-gemma3-4b

Typhoon2.1 4B - 4B parameters Thai / English bilingual LLM build based on Gemma3.

Details

Readme

Run

Performance