Heretic

community

https://github.com/p-e-w/heretic

Activity Feed

AI & ML interests

Abliteration, interpretability, training-free model modification, democratization of AI

Recent Activity

VINAY-UMRETHE new activity about 2 hours ago

heretic-org/Multilingual-Harmless-Harmful:[bot] Conversion to Parquet

VINAY-UMRETHE updated a bucket about 15 hours ago

heretic-org/Heretic-Grimoire-Storage

VINAY-UMRETHE updated a dataset 1 day ago

heretic-org/Multilingual-Harmless-Harmful

View all activity

darkc0de

posted an update 8 minutes ago

Post

Big shoutout to Abliterlitics.

These benchmark writeups are consistently some of the most thoughtful, detailed, and genuinely useful posts I read on open-weight model behavior and abliteration. The latest Qwen3.8-27B comparison is another great one.

I look forward to pretty much every post he puts out on the subject. If you're interested in uncensoring, abliteration, model behavior, or comparing techniques across models, definitely check his work out:

https://abliterlitics.dev

VINAY-UMRETHE

in heretic-org/Multilingual-Harmless-Harmful about 2 hours ago

[bot] Conversion to Parquet

#2 opened about 15 hours ago by

parquet-converter

VINAY-UMRETHE

updated a bucket about 15 hours ago

heretic-org/Heretic-Grimoire-Storage

2.1 MB

VINAY-UMRETHE

updated a dataset 1 day ago

heretic-org/Multilingual-Harmless-Harmful

Viewer • Updated 1 day ago • 6.66k • 31 • 1

VINAY-UMRETHE

in heretic-org/Multilingual-Harmless-Harmful 2 days ago

Add language marathi (mr).

#1 opened 2 days ago by

VINAY-UMRETHE

published a dataset 2 days ago

heretic-org/Multilingual-Harmless-Harmful

Viewer • Updated 1 day ago • 6.66k • 31 • 1

DavidAU

posted an update 3 days ago

Post

4843

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

3 replies

p-e-w

authored 2 papers 10 days ago

Don't Repeat Yourself: Stopping Verbatim Loops at Sampling Time

Paper • 2608.22761 • Published 14 days ago • 1

XTC: Head-Aware Sampling by Excluding Top Choices

Paper • 2608.22758 • Published 14 days ago • 2

DavidAU

posted an update 19 days ago

Post

18949

Qwen3.8 - 27B - COLD FUSION

Reduction in thinking tokens to 1/10 to 1/2 "normal Qwen" across all three modes of thinking without loss of detail in thinking or output.

Increase in general intelligence too (all 7 critical benches); bench marks posted.

Trained using the COLD FUSION method (GAIN + UNSLOTH).
NOTE: This is NOT a heretic / uncensored version.

MTP and GGUF NEO MAX quants:
DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-NM-DAU-NEO-MAX-MTP-GGUF

SOURCE:
DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1

7 replies

VINAY-UMRETHE

in heretic-org/Qwen3.8-27B-heretic-ara 20 days ago

Refuses basically everything

👍 1

#1 opened 21 days ago by

afkaf

DreamFast

in heretic-org/Qwen3.8-27B-heretic-ara 20 days ago

Refuses basically everything

👍 1

#1 opened 21 days ago by

afkaf

VINAY-UMRETHE

updated a collection 22 days ago

Qwen Cosmos

Collection

Collection of Qwen-Heretic Models. • 5 items • Updated 22 days ago • 3

VINAY-UMRETHE

updated a model 22 days ago

heretic-org/Qwen3.8-27B-heretic-ara

Image-Text-to-Text • 27B • Updated 22 days ago • 8.13k • • 33

VINAY-UMRETHE

updated a model 25 days ago

heretic-org/LFM2.5-VL-3B-heretic

Image-Text-to-Text • 3B • Updated 25 days ago • 155 • 4

VINAY-UMRETHE

published a model 25 days ago

heretic-org/LFM2.5-VL-3B-heretic

Image-Text-to-Text • 3B • Updated 25 days ago • 155 • 4

DavidAU

posted an update 26 days ago

Post

22330

Qwen3.6-40B-Fable-Fusion-6-Core-Deckard-Eleanor-Heretic-Uncensored

The fire of multiple Fable Fusion 711 cores in one, larger model.

This is the first 40B fine tune that reaches "closed source" (IE OpenAI, Claude) level of intelligence in both 8 bit and 4 bit.

This model is composed from multiple Qwen 27B Fable Fusion 711 cores (1700+ likes, 2.3 million+ downloads) - a record breaking model in terms of intelligence and raw power.

The "40B Eleanor" takes this to the next level with improvements in thinking tokens/ thinking block size (1/10 to 1/2 the size), thinking in general and output detail quality with deep analytics too.

- 1/10 to 1/2 the number of thinking tokens.
- Extreme depth of detail in generations, including long form, in depth analytics.
- STRONG creative abilities.
- Auto-variable reasoning: Model only reasons as much as the task requires.
- Strong general intelligence.
- It says what it means in less words, more clearly than any previous tuned model.
- It will go all in, in exacting detail when the situation calls for it.
- If it thinks something is wrong / wrong path it will say so too.

Regular and MTP Quants:

DavidAU/Qwen3.6-40B-Fable-Fusion-6-Core-Deckard-Eleanor-Heretic-Uncensored-NM-DAU-NEO-MAX-MTP-GGUF