Volko76/qwen2.5-instruct-french

Volko76/ qwen2.5-instruct-french:latest

114 Downloads Updated 1 year ago

Finetuned with LoRa on French Alpaca dataset

0.5b

ollama run Volko76/qwen2.5-instruct-french

curl http://localhost:11434/api/chat \
  -d '{
    "model": "Volko76/qwen2.5-instruct-french",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='Volko76/qwen2.5-instruct-french',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'Volko76/qwen2.5-instruct-french',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 year ago

1 year ago

753433844ed6 · 398MB ·

model

archqwen2

parameters494M

quantizationQ4_K_M

398MB

params

{ "stop": [ "### Instruction:" ] }

29B

template

{{ .System }} ### Instruction: {{ .Prompt }} ### Response:

59B

Readme

From the dataset : https://huggingface.co/datasets/Volko76/Alpaca_french_instruct/blob/main/README.md

HuggingFace model : https://huggingface.co/Volko76/Qwen2.5-0.5B-Instruct-French-LoRa-GGUF

A great french conversational SLM