heretic-org/Multilingual-Harmless-Harmful
Viewer • Updated • 6.66k • 3 • 1
Chroma
Chroma111
AI & ML interests
None yet
Recent Activity
liked a dataset about 11 hours ago
heretic-org/Multilingual-Harmless-Harmful liked a model 1 day ago
Jackrong/Qwopus3.8-27B-Flash upvoted a collection 1 day ago
⚡️Qwopus3.8Organizations
None yet
liked a
dataset about 11 hours ago
liked a
model 1 day ago
upvoted a collection 1 day ago
liked a
model 1 day ago
liked a
dataset 2 days ago
upvoted a paper 2 days ago
reacted to DavidAU's post with ❤️ 2 days ago
Post
4509
Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored
This is the first fine tune to exceed 730 "arc-c" ("735": 144 pts higher than Qwen 3.8 27B) AND 880 ARC-E (The OpenAI, Claude and Gemini "zone of intelligence") in 8 bit and over 718 arc-c in 4 bit.
This version is called TURBO because it drastically reduces thinking tokens (by 1/2 to as high as 1/10), yet maintains output detail and quality.
In other words while "reg" Qwen3.8 27B is thinking about "formatting" for a few 1000 tokens, this model is already done and waiting for more.
This repo contains both "regular" and "MTP" Neo-CODER MAX DI-MATRIX (duel imatrix) GGUF quants.
DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF
PS: There are 29 additional quant repos as of this writing too, as well NVFP4 and many more as well.
This is one of 10+ Qwen 3.8 27B at or above ARC-C of 717 (all 10 exceed all core benchmarks of Qwen 3.8, 3.6 and 3.5 27B and 35B-A3B versions) - you can see the complete project and some of the training here :
DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU
This is the first fine tune to exceed 730 "arc-c" ("735": 144 pts higher than Qwen 3.8 27B) AND 880 ARC-E (The OpenAI, Claude and Gemini "zone of intelligence") in 8 bit and over 718 arc-c in 4 bit.
This version is called TURBO because it drastically reduces thinking tokens (by 1/2 to as high as 1/10), yet maintains output detail and quality.
In other words while "reg" Qwen3.8 27B is thinking about "formatting" for a few 1000 tokens, this model is already done and waiting for more.
This repo contains both "regular" and "MTP" Neo-CODER MAX DI-MATRIX (duel imatrix) GGUF quants.
DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF
PS: There are 29 additional quant repos as of this writing too, as well NVFP4 and many more as well.
This is one of 10+ Qwen 3.8 27B at or above ARC-C of 717 (all 10 exceed all core benchmarks of Qwen 3.8, 3.6 and 3.5 27B and 35B-A3B versions) - you can see the complete project and some of the training here :
DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU
- 3 replies
upvoted 8
papers 2 days ago
H3-World: Turning Language Understanding into World Control
Paper • 2609.01560 • Published • 47
UI-Venus-2 Technical Report
Paper • 2609.00028 • Published • 61
Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling
Paper • 2608.30821 • Published • 106
DreamX-Creator: Democratizing Native Audio-Video Generation at 2K Resolution
Paper • 2608.31106 • Published • 98
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?
Paper • 2609.01437 • Published • 240
Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving
Paper • 2609.00111 • Published • 371
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills
Paper • 2609.02749 • Published • 520
StudentSim: Training LLM-based Student Simulators
Paper • 2609.01591 • Published • 481
liked a
dataset 2 days ago
liked 3
models 3 days ago
upvoted a paper 3 days ago