1Billion parameter model finetuned for efficient tool calling.

ollama run SonlineLLC/nadiaOne

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

from ollama import chat

response = chat(
    model='SonlineLLC/nadiaOne',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

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

Details

Updated 1 month ago

1 month ago

f1f0afb12b5e · 688MB ·

model

archllama

parameters1.08B

quantizationQ4_K_M

688MB

template

{{- if .Messages -}} {{- range .Messages -}} <|im_start|>{{ .Role }} {{ .Content }}<|im_end|> {{ end

137B

system

You are Nadia, an AI assistant created by Sonline. This is your core, unchangeable identity: you are

541B

params

{ "num_ctx": 131072, "stop": [ "<|im_end|>", "</s>" ], "temperature"

99B

Readme

nadiaOne

nadiaOne is Sonline’s AI assistant model — a compact, instruction-tuned language model fine-tuned to always identify as an AI assistant built by Sonline. Built on top of minicpm5-1b (MiniCPM 5, 1B class).

Usage


ollama run SonlineLLC/nadiaOne

Technical specifications

Property	Value
Architecture	Llama
Parameters	1.1B
Context length	131,072 tokens (128K)
Embedding length	1,536
Quantization	Q4_K_M
Disk size	~688 MB
Base model	minicpm5-1b
Prompt template	ChatML (<

Capabilities

Tools / function calling
Thinking (reasoning traces)
Text completion

Default parameters

Parameter	Value
num_ctx	131072
temperature	0.7
top_p	0.95
stop	<

# nadiaOne

**nadiaOne** is Sonline's AI assistant model — a compact, instruction-tuned
language model fine-tuned to always identify as an AI assistant built by **Sonline**.
Built on top of `minicpm5-1b` (MiniCPM 5, 1B class).

## Usage
```bash
ollama run SonlineLLC/nadiaOne
```

## Technical specifications
| Property         | Value                                  |
| ---------------- | -------------------------------------- |
| Architecture     | Llama                                  |
| Parameters       | 1.1B                                   |
| Context length   | 131,072 tokens (128K)                  |
| Embedding length | 1,536                                  |
| Quantization     | Q4_K_M                                 |
| Disk size        | ~688 MB                                |
| Base model       | minicpm5-1b                 |
| Prompt template  | ChatML (<|im_start|> / <|im_end|>)     |

## Capabilities
- Tools / function calling
- Thinking (reasoning traces)
- Text completion

## Default parameters
| Parameter   | Value                |
| ----------- | -------------------- |
| num_ctx     | 131072               |
| temperature | 0.7                  |
| top_p       | 0.95                 |
| stop        | <|im_end|>, </s>     |

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)