goekdenizguelmez/ Josie-R1

35 Downloads Updated 3 weeks ago

My (Gökdeniz Gülmez) first reasoning model fine-tuned on a custom distill dataset

tools thinking

ollama run goekdenizguelmez/Josie-R1

curl http://localhost:11434/api/chat \
  -d '{
    "model": "goekdenizguelmez/Josie-R1",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='goekdenizguelmez/Josie-R1',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'goekdenizguelmez/Josie-R1',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code ollama launch claude --model goekdenizguelmez/Josie-R1

Codex ollama launch codex --model goekdenizguelmez/Josie-R1

OpenCode ollama launch opencode --model goekdenizguelmez/Josie-R1

OpenClaw ollama launch openclaw --model goekdenizguelmez/Josie-R1

Models

View all →

Name

6 models

Size

Context

Input

Josie-R1:latest

2.5GB · 40K context window · Text · 3 weeks ago

Josie-R1:latest

2.5GB

40K

Text

Josie-R1:4b-q4_k_m

2.5GB · 40K context window · Text · 3 weeks ago

Josie-R1:4b-q4_k_m

2.5GB

40K

Text

Josie-R1:4b-q5_k_m

2.9GB · 40K context window · Text · 3 weeks ago

Josie-R1:4b-q5_k_m

2.9GB

40K

Text

Josie-R1:4b-q6_k

3.3GB · 40K context window · Text · 3 weeks ago

Josie-R1:4b-q6_k

3.3GB

40K

Text

Josie-R1:4b-q8_0

4.3GB · 40K context window · Text · 3 weeks ago

Josie-R1:4b-q8_0

4.3GB

40K

Text

Josie-R1:4b-f16

8.1GB · 40K context window · Text · 3 weeks ago

Josie-R1:4b-f16

8.1GB

40K

Text

Readme

JOSIE-R1-4B

The JOSIE-R1-4B models are reasoning-oriented language models trained on a custom distillation dataset derived from the original Josie-RL-Zero-V1 model. The training process emphasizes instruction fidelity, reasoning consistency, and practical usefulness across a wide range of everyday and technical tasks.

Model Card for Goekdeniz-Guelmez/JOSIE-R1-4B

Model Description

Introducing JOSIE-R1-4B, a new member of the JOSIE family, fine-tuned with a strong focus on openness, instruction alignment, and transparent reasoning behavior. The model is designed to follow user intent closely while retaining the expressive and occasionally unconventional character that defines the Josie lineage.

Benchmarks comming soon!

Developed by: Goekdeniz-Guelmez
Funded by: Goekdeniz-Guelmez
Shared by: Goekdeniz-Guelmez
Model type: qwen3
Finetuned from model: Qwen/Qwen3-4B