AI & ML interests

None defined yet.

mahwizzzzΒ 
posted an update 30 days ago
view post
Post
190
I implemented the attention-free bidirectional encoder architecture Avey-B for Urdu a compact 24.87M-parameter language encoder built for efficient Urdu NLP research.

Original Avey-B paper: Avey-B (2602.15814)
Urdu model: mahwizzzz/avey-b-ur


mahwizzzzΒ 
posted an update about 2 months ago
AFOliveiraΒ 
updated a Space 3 months ago
burtenshawΒ 
updated a Space 4 months ago
burtenshawΒ 
published a Space 4 months ago
mahwizzzzΒ 
posted an update 4 months ago
view post
Post
403
Released lafzyn , built over Qwen, an Urdu language model that converts Urdu text into IPA phonetic transcription, with GGUF builds for local inference.

Release contents:
- mahwizzzz/lafzyn: full weights
- mahwizzzz/lafzyn-gguf: quantized builds

Try it out πŸ€—
Demo: https://huggingface.co/spaces/mahwizzzz/Lafzyn
mahimairajaΒ 
posted an update 8 months ago
view post
Post
1284
πŸ”₯ Qwen is dominating the SLM space right now.

We all know this year 2026 is the year of Small Models, but Alibaba team took it bit serious it seems!

Qwen3-TTS β€” 3-sec voice cloning, 10 languages, beats ElevenLabs
Qwen3-ASR β€” Just dropped TODAY! 52 languages, <8% WER, SOTA open-source ASR
Qwen-Image β€” #1 open-source image model on AI Arena

All Apache 2.0. The most complete open-source AI stack, period.

So, what do you think now, what next release could be? an Language Model?
Comment below
  • 1 reply
Β·
mahimairajaΒ 
posted an update 9 months ago
mahimairajaΒ 
posted an update 9 months ago
view post
Post
1522
Lacking vllm support for Transformers v5, frustrating only me?
mahimairajaΒ 
posted an update 9 months ago
view post
Post
4801
Happy New Years 2026!

For next 365 days I will be commit to work on:

- Document AI and OCR Automations
- Voice Agents
- Long Running Tasks - Durable Agents
  • 1 reply
Β·
daavooΒ 
posted an update 10 months ago
view post
Post
1910
2025: The Year of Agents.
2026: The Year of Local Agents?

Relying on cloud-hosted LLMs is often overkill. While frontier models still lead in complex coding, local models are now more than capable of handling many agentic workflowsβ€”with zero latency and total privacy.

To help bridge the gap between local inference and usable agents, I’m releasing agent.cpp: https://github.com/mozilla-ai/agent.cpp

It provides minimal, high-performance building blocks for agents in C++, built directly around the awesome llama.cpp ecosystem.
Stop sending your data to a remote API. Start building and running agents on your own hardware.
  • 1 reply
Β·
daavooΒ 
posted an update about 1 year ago
view post
Post
192
A new minor version of any-agent (1.1.0 ) is out πŸš€

https://github.com/mozilla-ai/any-agent/releases/tag/1.1.0

- 🀏Improvements for Small Language Models
We recommend tinyagent to be used as default when working with Small Language Models.
- πŸ§ͺ Extending and Improving test suite.
For example, we now include a cookbook and an integration test running a Small Language Model (Qwen 1.7B)
- πŸ“–Extending and Improving docs
daavooΒ 
posted an update over 1 year ago
daavooΒ 
posted an update over 1 year ago
view post
Post
1559
Have you heard about the Agent2Agent Protocol (A2A)?

We have just released an option in https://github.com/mozilla-ai/any-agent to serve with A2A any of the supported agent frameworks (Agno, Google ADK, Langchain, LlamaIndex, OpenAI Agents SDK, smolagents and tinyagent)!

Check the docs https://mozilla-ai.github.io/any-agent/serving/

# google_expert.py
from any_agent import AgentConfig, AnyAgent
from any_agent.config import ServingConfig
from any_agent.tools import search_web

agent = AnyAgent.create(
    "google",
    AgentConfig(
        name="google_expert",
        model_id="gpt-4.1-nano",
        instructions="You must use the available tools to find an answer",
        description="An agent that can answer questions about the Google Agents Development Kit (ADK).",
        tools=[search_web]
    )
)

agent.serve(ServingConfig(port=5001))
daavooΒ 
posted an update over 1 year ago
view post
Post
1376
We've just released a new version of https://github.com/mozilla-ai/any-agent , including a Python implementation of https://huggingface.co/blog/tiny-agents!

Give it a ⭐!

from any_agent import AnyAgent, AgentConfig
from any_agent.config import MCPStdioParams

agent = AnyAgent.create(
    "tinyagent",
    AgentConfig(
        model_id="gpt-4.1-nano",
        instructions="You must use the available tools to find an answer",
        tools=[
            MCPStdioParams(
                command="uvx",
                args=["duckduckgo-mcp-server"]
            )
        ]
    )
)

result = agent.run(
    "Which Agent Framework is the best??"
)
print(result.final_output)