Guy DuGan II's picture

Guy DuGan II

gss1147

·

AI & ML interests

AI Code development, AI ChatBots, AI Research, LLM finetuning, llm merging, AI development

Recent Activity

liked a model 5 days ago

gss1147/IBM-Grok4-UltraFast-Coder-1B-GGUF

updated a collection 6 days ago

WithIn US AI (((GGUF MODELS))

updated a collection 6 days ago

WithIn US AI (((GGUF MODELS))

View all activity

Organizations

upvoted a collection 11 days ago

WithIn US AI (((GGUF MODELS))

LLM MODELS TRAINED, FINE-TUNED, MERGED BY (WITHIN US AI) • 9 items • Updated 6 days ago • 2

upvoted a collection 13 days ago

Qwen3.5-Claude-4.6-Opus-Reasoning-Distilled

18 items • Updated 4 days ago • 184

upvoted 3 collections 14 days ago

Llama 4

Llama 4 release • 13 items • Updated Apr 29, 2025 • 716

Meta's Llama 3.2 language models & evals

14 items • Updated Dec 13, 2024 • 401

OctoThinker-Llama-1B Family

What makes a base language model suitable for RL? Through controlled experiments, we identify key factors then leverage them to scale up mid-training. • 6 items • Updated Jul 6, 2025 • 3

upvoted a collection 21 days ago

DASD-Thinking

6 items • Updated Feb 3 • 24

upvoted a collection 22 days ago

Granite 4.0 Nano Language Models

Ultra-compact language models designed for the edge and on-device deployment. • 9 items • Updated 3 days ago • 100

upvoted a collection 27 days ago

FunctionGemma

3 items • Updated 24 days ago • 38

upvoted 2 collections about 1 month ago

Qwen3.5

21 items • Updated 27 days ago • 1.42k

GPT 5.2

Distilled models and datasets for GPT 5.2. • 7 items • Updated Mar 2 • 10

upvoted a collection about 2 months ago

Gemma 3 Release

28 items • Updated 24 days ago • 631

upvoted an article about 2 months ago

Article

Community Evals: Because we're done trusting black-box leaderboards over the community

+5

Feb 4

•

88

upvoted 8 collections about 2 months ago

Flan-T5 release

The Flan-T5 covers 4 checkpoints of different sizes each time. It also includes upgrades versions trained using Universal sampling • 7 items • Updated 24 days ago • 35

Kimi-K2

Moonshot's MoE LLMs with 1 trillion parameters, exceptional on agentic intellegence • 5 items • Updated Jan 27 • 173

Qwen3-Coder

5 items • Updated Dec 31, 2025 • 176

Qwen3-Next

4 items • Updated Dec 31, 2025 • 187

Qwen3-Omni

6 items • Updated Dec 31, 2025 • 195

Qwen3Guard

7 items • Updated Dec 31, 2025 • 65

Qwen3-VL

37 items • Updated Dec 31, 2025 • 684

Qwen3-VL-Embedding

2 items • Updated Jan 8 • 65