Supa-AI/malaysian-llama-3.2-3b-instruct:q4_k

Supa-AI/ malaysian-llama-3.2-3b-instruct:q4_k_m

202 Downloads Updated 1 year ago

Continue finetuning https://huggingface.co/meta-llama/Llama-3.2-3B on highly curated 1.5B tokens Malaysian instruction dataset.

ollama run Supa-AI/malaysian-llama-3.2-3b-instruct:q4_k_m

curl http://localhost:11434/api/chat \
  -d '{
    "model": "Supa-AI/malaysian-llama-3.2-3b-instruct:q4_k_m",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='Supa-AI/malaysian-llama-3.2-3b-instruct:q4_k_m',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'Supa-AI/malaysian-llama-3.2-3b-instruct:q4_k_m',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 year ago

1 year ago

1d2891aaf952 · 2.2GB ·

model

archllama

parameters3.61B

quantizationQ4_K_M

2.2GB

template

10B

license

Apache 2.0

10B

system

You are a helpful AI assistant. Original model: mesolitica/malaysian-Llama-3.2-3B-Instruct

90B

params

{ "stop": [ "User:", "Assistant:" ], "temperature": 0.7, "top_p": 0.

62B

Readme

This model was converted to GGUF format from mesolitica/malaysian-Llama-3.2-3B-Instruct using llama.cpp. Refer to the original model card for more details on the model.