Zsolt Zsoldos

zsolx2

https://ai4a.net/

zsolx2

AI & ML interests

LLM, DT, RF, IF, Multi Agent, Graph, RAG, etc.

Recent Activity

liked a model 24 days ago

sentence-transformers/all-MiniLM-L6-v2

liked a model about 1 month ago

microsoft/layoutlmv3-base

liked a model about 1 month ago

bartowski/Ministral-8B-Instruct-2410-HF-GGUF-TEST

View all activity

Organizations

None yet

zsolx2's activity

liked a model 24 days ago

sentence-transformers/all-MiniLM-L6-v2

liked 2 models about 1 month ago

microsoft/layoutlmv3-base

Updated Apr 10 • 1.47M • 336

bartowski/Ministral-8B-Instruct-2410-HF-GGUF-TEST

Text Generation • Updated Oct 16 • 9.73k • 16

liked a model about 2 months ago

nvidia/OpenMath2-Llama3.1-8B

Text Generation • Updated 3 days ago • 2.42k • 24

updated 2 models about 2 months ago

zsolx2/OpenMath2-Llama3.1-8B-Q4_0-GGUF

Updated Oct 4 • 4

zsolx2/Phi-3.5-mini-instruct_Uncensored-Q4_0-GGUF

Text Generation • Updated Sep 28 • 207

liked a model about 2 months ago

Qwen/Qwen2.5-Coder-7B-Instruct-GGUF

Text Generation • Updated 13 days ago • 51.8k • 62

liked 2 models 3 months ago

OpenGVLab/InternVL2-8B

Image-Text-to-Text • Updated 4 days ago • 128k • 148

internlm/internlm2_5-20b-chat

Text Generation • Updated Aug 20 • 1.09k • 83

updated a model 3 months ago

zsolx2/Phi-3.5-mini-instruct-Q4_0-GGUF

Text Generation • Updated Aug 22 • 31

liked 4 models 4 months ago

Reacted to appoose's post with 🔥 4 months ago

Post

1788

Excited to announce the release of our high-quality Llama-3.1 8B 4-bit HQQ/calibrated quantized model! Achieving an impressive 99.3% relative performance to FP16, it also delivers the fastest inference speed for transformers.

mobiuslabsgmbh/Llama-3.1-8b-instruct_4bitgs64_hqq_calib