Angelino Santiago's picture

Angelino Santiago

MrDevolver

·

AI & ML interests

None yet

Recent Activity

upvoted a collection 43 minutes ago

Qwen 3.5 - 0.8, 2, 4, 9, 27, 35B - regular / uncensored

replied to DavidAU's post about 1 hour ago

21 Qwen 3.5 Fine Tunes (thinking and instruct) ; reg and uncensored (2B to 27B) exceed benchmarks, and work better than org models. All are bench marked against org model. Many exceed all benchmarks of org model. Claude, GLM, Gemini and other distills. Thinking AND dedicated Instruct versions. Core goal: Increase benchmarks, and address long thinking blocks. Highlights: 9B and 27B instruct "Claude" versions hit 624 and 675 on the "ARC-C" (hard challenge). Thinking fine tunes exceed org model performance (in thinking mode). In many cases there is a drastic reduction in thinking block size. 9B Claude Heretic Uncensored, GGUF : -Neo, Code Imatrix (duel imatrix) - Updated Jinja template - Custom tensor enhancements. https://huggingface.co/DavidAU/Qwen3.5-9B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-MAX-NEOCODE-Imatrix-GGUF COLLECTION [21 models]: https://huggingface.co/collections/DavidAU/qwen-35-08-2-4-9-27-35b-regular-uncensored

liked a model about 24 hours ago

GOBA-AI-Labs/PrunedHub-Qwen3.5-35B-A3B-80pct

View all activity

Organizations

upvoted a collection 43 minutes ago

Qwen 3.5 - 0.8, 2, 4, 9, 27, 35B - regular / uncensored

Min 256k context + images : Reg, Heretic, Heretic fine tunes of Qwen 3.5 in all sizes. • 22 items • Updated 2 days ago • 11

upvoted a collection 8 days ago

Qwen3.5

21 items • Updated 2 days ago • 1.12k

upvoted a collection 25 days ago

OmniDimen-2

3 items • Updated 25 days ago • 3

upvoted a collection 3 months ago

My models: daily driver rotation

A rotating list of models I created and currently use as daily drivers. From my many models, these are the ones I’m actively using. • 6 items • Updated 7 days ago • 7

upvoted a collection 4 months ago

GLM-4.6

2 items • Updated 9 days ago • 52

upvoted a collection 5 months ago

Good RP Models

List of models for extremely dark NSFW roleplay that I tested. The best models will be on top of the list (mostly). • 28 items • Updated 5 days ago • 96

upvoted a collection 6 months ago

Granite 4.0 Language Models

13 items • Updated Nov 17, 2025 • 210

upvoted a collection 8 months ago

T5Gemma

32 items • Updated Jul 10, 2025 • 81

upvoted a collection 10 months ago

NextCoder

NextCoder family of code-editing LMs developed with Selective Knowledge Transfer and its training data. • 6 items • Updated Jul 9, 2025 • 74

upvoted 4 collections 11 months ago

Qwen3

84 items • Updated Dec 31, 2025 • 1.71k

Qwen3

Qwen's new Qwen3 models. In Unsloth Dynamic 2.0, GGUF, 4-bit and 16-bit Safetensor formats. Includes 128K Context Length variants. • 70 items • Updated 4 days ago • 264

GLM-4-0414

GLM-4-0414 series model • 6 items • Updated 9 days ago • 134

SkyReels-V2

Infinite-length Film Generative Model • 17 items • Updated Jun 14, 2025 • 75

upvoted a paper 11 months ago

PRIMA.CPP: Speeding Up 70B-Scale LLM Inference on Low-Resource Everyday Home Clusters

Paper • 2504.08791 • Published Apr 7, 2025 • 139

upvoted 5 collections 11 months ago

Cogito v1 Preview

5 items • Updated Apr 8, 2025 • 119

Skywork-OR1

Skywork Open Reasoner 1 • 8 items • Updated 9 days ago • 31

Granite 3.3 Language Models

Our latest language models licensed under Apache 2.0 license. • 4 items • Updated Nov 17, 2025 • 45

SANA-Sprint

🏃SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation • 6 items • Updated 1 day ago • 43

YandexGPT-5-Lite-8B

3 items • Updated Mar 31, 2025 • 10

upvoted a paper 12 months ago

Small Models Struggle to Learn from Strong Reasoners

Paper • 2502.12143 • Published Feb 17, 2025 • 39