w4d4f4k/ aiia_v1

3 Downloads Updated 3 weeks ago

Based on llama3.2 4b instruct

ollama run w4d4f4k/aiia_v1

curl http://localhost:11434/api/chat \
  -d '{
    "model": "w4d4f4k/aiia_v1",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='w4d4f4k/aiia_v1',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'w4d4f4k/aiia_v1',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Models

Name

1 model

Size / Usage

Context

Input

aiia_v1:latest

2.0GB · 128K context window · Text · 3 weeks ago

aiia_v1:latest

2.0GB

128K

Text

Readme

AIIA Llama3.2 Agent 3B

Llama-3.2-3B-Instruct fine-tuned for the AIIA agent framework — an
autonomous PLAN/BUILD-mode code agent with XML-style tool calling.

What it does

Executes coding and file-system tasks step by step using AIIA’s tool
protocol:

<WriteFile>                                                                                                                                                        
<fileName>fibonacci.py</fileName>                                                                                                                                  
<contentOfFile>def fibonacci(n): ...</contentOfFile>                                                                                                               
</WriteFile>

Supported tools include: ReadFile, WriteFile, CreateFile, AppendFile,
TreeView, List, Find, Grep, ReplaceLine, Sed, Diff, ExecuteScript, Terminal,
createPlan, nextTask, and more. Task lifecycle is signalled with
<nextTask>completed</nextTask> / <nextTask>blocked</nextTask>.

Training

Base: meta-llama/Llama-3.2-3B-Instruct (Llama 3.2 Community License)
Data: ~2,300 real AIIA agent trajectories (file I/O, shell execution, code editing, planning, multi-step task completion) in native Llama-3 chat format
Quantization: Q4_K_M GGUF (2.0 GB)

Usage

Designed to run inside the AIIA framework, which injects real tool results and drives the task loop.

ollama run w4d4f4k/aiia_v1

Recommended options: temperature 0.3-0.7 for BUILD mode.

Compared to w4d4f4k/qwen3_v1

	aiia_v1 (this)	qwen3_v1
Base	Llama-3.2-3B	Qwen3-4B-Instruct-2507
Size (Q4_K_M)	2.0 GB	2.5 GB
Speed / power	lighter, faster	~25% heavier
Coding ability	good	stronger

Use this one for lighter tasks and lower power draw; use qwen3_v1 when coding quality matters most.

Limitations

Specialized for AIIA’s XML tool format; not a general chat model.
Tool results must be provided by the calling framework; the model does not execute anything itself.
English-focused, matching the training trajectories.

Requirements

~2.5 GB VRAM/RAM for Q4_K_M + context
Runs on stock Ollama, llama.cpp, LM Studio — no custom runtime needed

# AIIA Llama3.2 Agent 3B                                                                                                                                           
                                                                                                                                                                   
Llama-3.2-3B-Instruct fine-tuned for the **AIIA agent framework** — an                                                                                             
autonomous PLAN/BUILD-mode code agent with XML-style tool calling.                                                                                                 
                                                                                                                                                                   
## What it does                                                                                                                                                    
                                                                                                                                                                   
Executes coding and file-system tasks step by step using AIIA's tool                                                                                               
protocol:                                                                                                                                                          
                                                                                                                                                                   
```                                                                                                                                                                
<WriteFile>                                                                                                                                                        
<fileName>fibonacci.py</fileName>                                                                                                                                  
<contentOfFile>def fibonacci(n): ...</contentOfFile>                                                                                                               
</WriteFile>                                                                                                                                                       
```                                                                                                                                                                
                                                                                                                                                                   
Supported tools include: ReadFile, WriteFile, CreateFile, AppendFile,                                                                                              
TreeView, List, Find, Grep, ReplaceLine, Sed, Diff, ExecuteScript, Terminal,                                                                                       
createPlan, nextTask, and more. Task lifecycle is signalled with                                                                                                   
`<nextTask>completed</nextTask>` / `<nextTask>blocked</nextTask>`.
 
## Training
 
- **Base:** meta-llama/Llama-3.2-3B-Instruct (Llama 3.2 Community License)
- **Data:** ~2,300 real AIIA agent trajectories (file I/O, shell execution,
  code editing, planning, multi-step task completion) in native Llama-3
  chat format
- **Quantization:** Q4_K_M GGUF (2.0 GB)
 
## Usage
 
Designed to run **inside the AIIA framework**, which injects real tool
results and drives the task loop.
 
```bash
ollama run w4d4f4k/aiia_v1
```
 
Recommended options: `temperature 0.3-0.7` for BUILD mode.
 
## Compared to w4d4f4k/qwen3_v1
 
| | aiia_v1 (this) | qwen3_v1 |
|---|---|---|
| Base | Llama-3.2-3B | Qwen3-4B-Instruct-2507 |
| Size (Q4_K_M) | 2.0 GB | 2.5 GB |
| Speed / power | lighter, faster | ~25% heavier |
| Coding ability | good | stronger |
 
Use this one for lighter tasks and lower power draw; use `qwen3_v1` when
coding quality matters most.
 
## Limitations
 
- Specialized for AIIA's XML tool format; not a general chat model.
- Tool results must be provided by the calling framework; the model does
  not execute anything itself.
- English-focused, matching the training trajectories.
 
## Requirements
 
- ~2.5 GB VRAM/RAM for Q4_K_M + context
- Runs on stock Ollama, llama.cpp, LM Studio — no custom runtime needed

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