Testing again Italian to English, and English to Italian with a Qwen2.5B 3B fine-tune, Whisper and TowerInstruct-7B-v0.2
Massimo Roberto Scamarcia PRO
mrs83
AI & ML interests
Natural Language Processing, Text Generation, Question Answering, Data Augmentation, Knowledge Transfer, Chain-of-Thought
Recent Activity
updated
a collection
24 days ago
Kurtis E1
updated
a collection
24 days ago
Kurtis E1
new activity
24 days ago
ethicalabs/Kurtis-E1.1-Qwen3-4B:Kurtis E1: A Voice for Empathy in the Tapestry of Consciousness
Organizations
mrs83's activity
replied to
their
post
about 2 months ago
reacted to
Steven10429's
post with 👀
2 months ago
Post
2889
I got rejected from llama4.
So that means I can use quantinized model without following their TOS.
Interesting. (JK)
So that means I can use quantinized model without following their TOS.
Interesting. (JK)
- 3 replies
replied to
their
post
3 months ago
https://huggingface.co/blog/mrs83/kurtis-e11-qwen25-3b-instruct
Question for Kurtis: Do you think training AI models on copyrighted material without consent is similar to the exploitation of nature in Princess Mononoke? In the film, the forest gods are sacrificed for industrial gain. Are artists today the forest spirits of our digital age, being consumed to fuel the progress of AI? How can we build AI that respects creative ecosystems instead of draining them?
Kurtis replies: .... Artists today do represent our digital age's "forest gods" or creators whose works can be used for various purposes, often including the development of cutting-edge technologies like AI. However, this does not negate their right to consent and control over their creative output. The exploitation you describe in Princess Mononoke could mirror scenarios where intellectual property is mishandled—whether that involves direct theft or misappropriation ...
posted
an
update
3 months ago
Post
1761
To developers: Build opt-in systems.
To policymakers: Legislate data transparency.
To artists: Unionize.
To users: Demand ethical tools.
To policymakers: Legislate data transparency.
To artists: Unionize.
To users: Demand ethical tools.
-
- 1 reply
replied to
their
post
3 months ago
Testing it right now with https://huggingface.co/Unbabel/TowerInstruct-7B-v0.2
Text is translated from German to English, sent to the LLM and translated back from English to German
posted
an
update
3 months ago
Post
3219
🚀 Just released a PoC: Kurtis-E1 MLX Voice Agent
An offline, privacy-first voice assistant built for macOS (Apple Silicon), designed for empathetic, short-form interactions.
🧠 Powered by:
- Whisper (via MLX) for speech-to-text: https://pypi.org/project/mlx-whisper/
- Kurtis-E1 (a custom SmolLM2 LLM) via Ollama
- Coqui-TTS XTTSv2 for multilingual TTS
- Optional translation layer via TowerInstruct-13B-v0.1 for non-English voice input/output: Unbabel/TowerInstruct-13B-v0.1
🎧 Everything runs entirely on-device (Mac Mini M4 Max - 24gb) — no cloud, no remote API calls, no data leakage.
💡 Code is fully handcrafted (no AI-generated code), and designed to showcase what’s possible with local models, even on laptops.
🛠️ Open to contributions, ideas (e.g., LM Studio for MLX inference, MLX worker subprocess, optimize for latency and VRAM usage).
👉 Video demo (Italian): https://www.youtube.com/watch?v=8-1PcmUStaI
PoC: https://github.com/ethicalabs-ai/Kurtis-E1-MLX-Voice-Agent
Kurtis-E1: ethicalabs/kurtis-e1-67a9148e0836885c44c7902c
Kurtis-E1 WebGPU: ethicalabs/Kurtis-E1-WebGPU
An offline, privacy-first voice assistant built for macOS (Apple Silicon), designed for empathetic, short-form interactions.
🧠 Powered by:
- Whisper (via MLX) for speech-to-text: https://pypi.org/project/mlx-whisper/
- Kurtis-E1 (a custom SmolLM2 LLM) via Ollama
- Coqui-TTS XTTSv2 for multilingual TTS
- Optional translation layer via TowerInstruct-13B-v0.1 for non-English voice input/output: Unbabel/TowerInstruct-13B-v0.1
🎧 Everything runs entirely on-device (Mac Mini M4 Max - 24gb) — no cloud, no remote API calls, no data leakage.
💡 Code is fully handcrafted (no AI-generated code), and designed to showcase what’s possible with local models, even on laptops.
🛠️ Open to contributions, ideas (e.g., LM Studio for MLX inference, MLX worker subprocess, optimize for latency and VRAM usage).
👉 Video demo (Italian): https://www.youtube.com/watch?v=8-1PcmUStaI
PoC: https://github.com/ethicalabs-ai/Kurtis-E1-MLX-Voice-Agent
Kurtis-E1: ethicalabs/kurtis-e1-67a9148e0836885c44c7902c
Kurtis-E1 WebGPU: ethicalabs/Kurtis-E1-WebGPU
-
- 3 replies
reacted to
BrigitteTousi's
post with 👍
3 months ago
Post
3742
Regardless of X being down or not, so glad I can rely on HF Posts for AI news ❤️🤗
-
- 1 reply
reacted to
Jaward's
post with 🔥
4 months ago
Post
3924
Finally here it is: a faster, custom, scalable GRPO trainer for smaller models with < 500M params, can train on 8gb ram cpu, also supports gpu for sanity sake (includes support for vllm + flash attention). Using smolLM2-135M/360M-instructs as ref & base models. Experience your own “aha” moment 🐳 on 8gb ram.
Code: https://github.com/Jaykef/ai-algorithms/blob/main/smollm2_360M_135M_grpo_gsm8k.ipynb
Code: https://github.com/Jaykef/ai-algorithms/blob/main/smollm2_360M_135M_grpo_gsm8k.ipynb
- 2 replies