Shawon Ashraf
shawon
AI & ML interests
Multi-Modal ML, Learning Dynamics in Larger Models, XAI
Recent Activity
reacted
to
gokaygokay's
post
with 🔥
4 days ago
FlashPack: Lightning-Fast Model Loading for PyTorch
https://github.com/fal-ai/flashpack
FlashPack — a new, high-throughput file format and loading mechanism for PyTorch that makes model checkpoint I/O blazingly fast, even on systems without access to GPU Direct Storage (GDS).
With FlashPack, loading any model can be 3–6× faster than with the current state-of-the-art methods like accelerate or the standard load_state_dict() and to() flow — all wrapped in a lightweight, pure-Python package that works anywhere.
updated
a model
15 days ago
shawon/Qwen3_14B_16bit-mlx-8Bit
published
a model
15 days ago
shawon/Qwen3_14B_16bit-mlx-8Bit
Organizations
-
PointArena: Probing Multimodal Grounding Through Language-Guided Pointing
Paper • 2505.09990 • Published • 12 -
Style Customization of Text-to-Vector Generation with Image Diffusion Priors
Paper • 2505.10558 • Published • 15 -
Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis
Paper • 2505.10046 • Published • 9 -
X-Sim: Cross-Embodiment Learning via Real-to-Sim-to-Real
Paper • 2505.07096 • Published • 5
-
PointArena: Probing Multimodal Grounding Through Language-Guided Pointing
Paper • 2505.09990 • Published • 12 -
Style Customization of Text-to-Vector Generation with Image Diffusion Priors
Paper • 2505.10558 • Published • 15 -
Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis
Paper • 2505.10046 • Published • 9 -
X-Sim: Cross-Embodiment Learning via Real-to-Sim-to-Real
Paper • 2505.07096 • Published • 5
models
16
shawon/Qwen3_14B_16bit-mlx-8Bit
Text Generation
•
15B
•
Updated
•
101
shawon/orpheus_3B_tts_16bit-mlx-4Bit
Text Generation
•
0.5B
•
Updated
•
82
shawon/orpheus_3B_tts_16bit
Text Generation
•
3B
•
Updated
•
40
shawon/llama3.1_8B_16bit-mlx-8Bit
Text Generation
•
8B
•
Updated
•
130
shawon/llama3.1_8B_16bit-mlx-4Bit
Text Generation
•
1B
•
Updated
•
64
shawon/gpt-oss-20B-mxfp4-mlx-4Bit
Text Generation
•
21B
•
Updated
•
215
shawon/gemma-3N-finetune-mlx-4Bit
Image-Text-to-Text
•
1B
•
Updated
•
100
shawon/Qwen3_14B_16bit-mlx-4Bit
Text Generation
•
15B
•
Updated
•
63
shawon/Qwen3_14B_16bit-Q8_0-GGUF
15B
•
Updated
•
24
shawon/Qwen3_14B_16bit-Q4_K_M-GGUF
15B
•
Updated
•
9