cnmoro/mistral_7b_portuguese:q4_K

cnmoro/ mistral_7b_portuguese:q4_K_S

724 Downloads Updated 1 year ago

A finetuned version of Mistral-7B-Instruct-v0.2 on a instruct portuguese dataset, as an attempt to improve the performance of the model on the language. HF Page: cnmoro/Mistral-7B-Portuguese

ollama run cnmoro/mistral_7b_portuguese:q4_K_S

curl http://localhost:11434/api/chat \
  -d '{
    "model": "cnmoro/mistral_7b_portuguese:q4_K_S",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='cnmoro/mistral_7b_portuguese:q4_K_S',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'cnmoro/mistral_7b_portuguese:q4_K_S',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 year ago

1 year ago

08fa560c4cc2 · 4.1GB ·

model

archllama

parameters7.24B

quantizationQ4_K_S

4.1GB

template

<s>[INST] {{ .Prompt }} [/INST]

31B

Readme

This is a finetuned version of mistralai/Mistral-7B-Instruct-v0.2 using unsloth on a instruct portuguese dataset, as an attempt to improve the performance of the model on the language.

No benchmarks have been executed yet.

Dataset used: cnmoro/WizardVicuna-PTBR-Instruct-Clean