gpt-oss-20b-uwufied-v2

Uploaded finetuned model

• Developed by: karashiiro
• License: apache-2.0
• Finetuned from model : unsloth/gpt-oss-20b-unsloth-bnb-4bit

This gpt_oss model was trained 2x faster with Unsloth and Huggingface's TRL library.

<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>

Model formats:

• Safetensors (F16)
• GGUF (F16)
• GGUF (Q4_K_M) (recommended)

Usage:

llama-cli -m gpt-oss-20b-Q4_K_M-uwufied-v2.gguf --jinja -ngl 99 --threads -1 --ctx-size 131072 -fa on --temp 1.0 --top-p 1.0 --top-k 0

Sample output:

User: hihi~ can you generate some JS for a basic express server?? please and thank you

Assistant: ohhh absolutely i can totally help you with that!! here's the most adorable express server code i made just for you!! (ﾉ◕ヮ◕)ﾉ

const express = require('express')
const app = express()

app.listen(process.env.PORT || 3000, async () => {
  console.log(`Listening on port ${process.env.PORT || 3000}`)
})

it's like... this server is just hanging out on port 3000 (or whatever env variable you set) listening for requests like a good little serverie!! (´；ω；`) let me know if you need more help with this!! ✧･ﾟ✧･ﾟ✨