Fine-Tuning xLSTM-7B on a budget: An Experimental Journey with Chat Templates
•
1
AI & ML interests
Building practical, ethical and sustainable AI/ML projects.
Recent Activity
Articles
Dual-State Recurrent Neural Network
-
ethicalabs/Echo-DSRN-114M-v0.1.2
Text Generation • 0.1B • Updated • 24.5k -
ethicalabs/Echo-SmolTools-114M-Intent-PEFT
Text Generation • Updated • 270 -
ethicalabs/Echo-SmolTools-114M-NSFW-CLF-PEFT
Text Generation • Updated • 150 -
ethicalabs/FlowerTune-Echo-DSRN-114M-Finance-PEFT
Text Generation • Updated • 174
The Empathetic Assistant (v1.2)
A Multimodal Deep Learning Approach for Skin Cancer Classification by using ViTs (Visual Transformers)
-
ethicalabs/Flwr-Qwen3-4B-Coding-PEFT
Text Generation • Updated -
ethicalabs/FlowerTune-Qwen2.5-Coder-0.5B-Instruct-PEFT
Text Generation • Updated • 5 -
ethicalabs/Flwr-Phi-4-mini-Instruct-Coding-PEFT
Text Generation • Updated • 16 • 1 -
ethicalabs/Flwr-SmolLM2-1.7B-Instruct-Coding-PEFT
Text Generation • Updated
Granite 4.0 Language Models for macOS (MLX-LM) - 4-bit Quantization
The Empathetic Assistant.
-
ethicalabs/Kurtis-E1.1-Qwen3-4B
Text Generation • 4B • Updated • 188 -
ethicalabs/Kurtis-E1.1-Qwen3-4B-GGUF
Text Generation • 4B • Updated • 14 -
ethicalabs/Kurtis-E1.1-Qwen2.5-3B-Instruct
Text Generation • 3B • Updated • 10 • • 1 -
ethicalabs/Kurtis-E1.1-Qwen2.5-0.5B-Instruct
Text Generation • 0.5B • Updated • 9 •
Language Model
Synthetic Datasets for SLMs fine-tuning.
Self-Improving LLMs Through Iterative Refinement
Dual-State Recurrent Neural Network
-
ethicalabs/Echo-DSRN-114M-v0.1.2
Text Generation • 0.1B • Updated • 24.5k -
ethicalabs/Echo-SmolTools-114M-Intent-PEFT
Text Generation • Updated • 270 -
ethicalabs/Echo-SmolTools-114M-NSFW-CLF-PEFT
Text Generation • Updated • 150 -
ethicalabs/FlowerTune-Echo-DSRN-114M-Finance-PEFT
Text Generation • Updated • 174
The Empathetic Assistant.
-
ethicalabs/Kurtis-E1.1-Qwen3-4B
Text Generation • 4B • Updated • 188 -
ethicalabs/Kurtis-E1.1-Qwen3-4B-GGUF
Text Generation • 4B • Updated • 14 -
ethicalabs/Kurtis-E1.1-Qwen2.5-3B-Instruct
Text Generation • 3B • Updated • 10 • • 1 -
ethicalabs/Kurtis-E1.1-Qwen2.5-0.5B-Instruct
Text Generation • 0.5B • Updated • 9 •
The Empathetic Assistant (v1.2)
Language Model
A Multimodal Deep Learning Approach for Skin Cancer Classification by using ViTs (Visual Transformers)
Synthetic Datasets for SLMs fine-tuning.
-
ethicalabs/Flwr-Qwen3-4B-Coding-PEFT
Text Generation • Updated -
ethicalabs/FlowerTune-Qwen2.5-Coder-0.5B-Instruct-PEFT
Text Generation • Updated • 5 -
ethicalabs/Flwr-Phi-4-mini-Instruct-Coding-PEFT
Text Generation • Updated • 16 • 1 -
ethicalabs/Flwr-SmolLM2-1.7B-Instruct-Coding-PEFT
Text Generation • Updated
Granite 4.0 Language Models for macOS (MLX-LM) - 4-bit Quantization
Self-Improving LLMs Through Iterative Refinement