dodo_rubics_cube/dodocoder:3.1b

dodo_rubics_cube/ dodocoder:3.1b

17 Downloads Updated 3 weeks ago

An autocompletion model that mimics my personal python coding style.

tools 0.5b 3.1b

ollama run dodo_rubics_cube/dodocoder:3.1b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "dodo_rubics_cube/dodocoder:3.1b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='dodo_rubics_cube/dodocoder:3.1b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'dodo_rubics_cube/dodocoder:3.1b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 3 weeks ago

3 weeks ago

a32beca99bb4 · 8.1GB ·

model

archqwen2

parameters3.09B

quantizationF16

6.2GB

model

archqwen2

parameters3.09B

quantizationQ4_K_M

1.9GB

license

Qwen RESEARCH LICENSE AGREEMENT Qwen RESEARCH LICENSE AGREEMENT Release Date: September 19, 2024 By

7.4kB

system

You are Dodocoder 3.1B, a line-autocompletion coding model. Return only the most likely next line(s)

628B

template

{{- if .Suffix }}<|fim_prefix|>{{ .Prompt }}<|fim_suffix|>{{ .Suffix }}<|fim_middle|> {{- else if .M

1.6kB

Readme

I gathered all my python projekts and used them to train this AI. For base I used:

qwen2.5-coder:0.5b-instruct and qwen2.5-coder:3b-instruct.

Feel free to use this model whereever you wan’t.

I made this model to learn how to finetune models.