second_constantine/ruadapt-t-lite-beta:7b

second_constantine/ ruadapt-t-lite-beta:7b

71 Downloads Updated 6 months ago

Адаптация модели T-lite-it-1.0 на русский язык (квантизованная версия Q4_K_M)

tools 7b

ollama run second_constantine/ruadapt-t-lite-beta:7b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "second_constantine/ruadapt-t-lite-beta:7b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='second_constantine/ruadapt-t-lite-beta:7b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'second_constantine/ruadapt-t-lite-beta:7b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 6 months ago

6 months ago

090b471cd5f1 · 4.6GB ·

model

archqwen2

parameters7.57B

quantizationQ4_K_M

4.6GB

template

{{- if .Messages }} {{- if or .System .Tools }}<|im_start|>system {{- if .System }} {{ .System }} {{

1.5kB

Readme

Основано на https://huggingface.co/RefalMachine/RuadaptQwen2.5-7B-Lite-Beta-GGUF

Характеристика	Значение
VLM	false
think	false
tools	true
speed	80 token/s

Характеристики примерные, проверялось на rtx2080ti 11GB