Swap base model: Qwen/Qwen3.6-35B-A3B → llmfan46 Heretic (uncensored)

Repoint the immediate base from vanilla Qwen/Qwen3.6-35B-A3B to
llmfan46/Qwen3.6-35B-A3B-uncensored-heretic, an uncensored "Heretic"
abliteration of the same 35B-A3B MoE (qwen3_5_moe-stamped, so the Architecture
section and the bundled blob's loadability are unchanged). Mirrors the dense
sibling's swap (Thanatos-27B -> llmfan46 27B Heretic v2).

The name Janus-35B, the janus Ollama tag, the FoolDev/Janus-35B URL, and the
Claude Fable 5 teacher slot are all kept.

- README: base_model + base_model_relation: finetune; heretic/uncensored tags
(library_name: transformers kept); badge, tagline, fact line, fork paragraph,
safetensors pointer, Related-models table, Credits, and the uncensored-base
known-limitation reframed to the Heretic lineage. Qwen/Qwen3.6-35B-A3B still
credited as the upstream pre-Heretic base. Added a bundled-blob-status callout
and Heretic-GGUF / MTP-Preserved variant rows; updated the Thanatos sibling
row to its own new Heretic base.
- CITATION.cff: title, abstract, keywords, references (immediate + upstream).
- banner.svg subtitle updated; banner.png re-rasterized from the SVG.
- Bundled Janus-35B-A3B.Q4_K_M.gguf left unchanged (legacy pre-Heretic quant;
rebundle pending, documented in the README callout).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

CHANGELOG.md

@@ -8,6 +8,33 @@ track the **tooling and documentation**, not the underlying base model.
 
 ## [Unreleased]
 
+### Changed (base swap → llmfan46 Heretic)
+- **Swapped the immediate base from `Qwen/Qwen3.6-35B-A3B` (vanilla) →
+  [`llmfan46/Qwen3.6-35B-A3B-uncensored-heretic`](https://huggingface.co/llmfan46/Qwen3.6-35B-A3B-uncensored-heretic)**
+  — an uncensored "Heretic" abliteration of the same Qwen 3.6 35B-A3B MoE
+  (`qwen3_5_moe`-stamped like the vanilla base, so the Architecture section,
+  the MoE-routing framing, and the bundled blob's loadability are all
+  unchanged). Mirrors the dense sibling's swap (`FoolDev/Thanatos-27B` →
+  `llmfan46/Qwen3.6-27B-uncensored-heretic-v2`). Repo name `Janus-35B`, the
+  `janus` Ollama tag, the `FoolDev/Janus-35B` URL, and the Claude Fable 5
+  teacher slot are all unchanged.
+  - README: frontmatter `base_model:` + `base_model_relation: finetune`;
+    `heretic` / `uncensored` tags added (`library_name: transformers` kept).
+    Base badge, tagline, fact line (`Type: Distilled + Abliterated MoE`), fork
+    paragraph, safetensors pointer, Related-models table, Credits, and the
+    "uncensored base" known-limitation reframed to the Heretic lineage.
+    `Qwen/Qwen3.6-35B-A3B` is still referenced as the upstream pre-Heretic base.
+    Added a "Bundled blob status" callout and the Heretic-GGUF /
+    MTP-Preserved variant rows. The Thanatos sibling row updated to its own
+    new Heretic base.
+  - `CITATION.cff`: title, abstract, keywords, and references reframed to the
+    Heretic base (immediate base + upstream base both cited).
+  - `banner.svg` subtitle → "Qwen 3.6 Heretic · MoE 35B/3B · Fable 5";
+    `banner.png` re-rasterized from the updated SVG.
+  - **Bundled `Janus-35B-A3B.Q4_K_M.gguf` unchanged** — still the legacy
+    pre-Heretic Qwen quant, so it loads and behaves like vanilla Qwen 3.6
+    35B-A3B until a Heretic rebundle ships (documented in the README callout).
+
 ### Changed (support badge → Tokyo Night banner)
 - **Replaced the shields.io "Buy me a coffee" badge** in the README badge
   row with a custom `bmc-banner.svg` support banner, themed to match

CITATION.cff

@@ -1,5 +1,5 @@
 cff-version: 1.2.0
-title: "Janus-35B: A Mixture-of-Experts Distillation Wrapper for Qwen 3.6 35B-A3B"
+title: "Janus-35B: A Mixture-of-Experts Distillation Wrapper for llmfan46's Qwen 3.6 35B-A3B Uncensored Heretic"
 message: "If you use this model card or its accompanying files, please cite as below."
 type: software
 authors:
@@ -8,15 +8,15 @@ authors:
 repository-code: "https://huggingface.co/FoolDev/Janus-35B"
 url: "https://huggingface.co/FoolDev/Janus-35B"
 abstract: >-
-  Janus-35B is a personal repackaging of the Qwen 3.6 35B-A3B
-  mixture-of-experts base model (35B total / 3B active per token,
-  256 experts, 8 activated) with Claude Fable 5 in the reasoning
-  teacher slot. The repository ships an Ollama Modelfile, the HF
-  Ollama-bridge files (template / system / params), sampling defaults,
-  and a bundled Q4_K_M GGUF (~19 GB) so the HF "Use this model" widget
-  surfaces a one-liner Ollama snippet. Other quants and the upstream
-  safetensors (Qwen/Qwen3.6-35B-A3B) are pulled from upstream on demand
-  rather than redistributed.
+  Janus-35B is a personal repackaging of llmfan46's uncensored Heretic
+  abliteration of the Qwen 3.6 35B-A3B mixture-of-experts base (35B
+  total / 3B active per token, 256 experts, 8 activated) with Claude
+  Fable 5 in the reasoning teacher slot. The repository ships an Ollama
+  Modelfile, the HF Ollama-bridge files (template / system / params),
+  sampling defaults, and a bundled Q4_K_M GGUF (~19 GB) so the HF "Use
+  this model" widget surfaces a one-liner Ollama snippet. Other quants
+  and the Heretic safetensors (llmfan46/Qwen3.6-35B-A3B-uncensored-heretic)
+  are pulled from upstream on demand rather than redistributed.
 keywords:
   - qwen
   - qwen3.6
@@ -25,10 +25,17 @@ keywords:
   - distillation
   - reasoning
   - llm
+  - heretic
+  - uncensored
 license: Apache-2.0
 references:
   - type: software
-    title: "Qwen3.6-35B-A3B"
+    title: "Qwen3.6-35B-A3B-uncensored-heretic (immediate base)"
+    authors:
+      - name: llmfan46
+    url: "https://huggingface.co/llmfan46/Qwen3.6-35B-A3B-uncensored-heretic"
+  - type: software
+    title: "Qwen3.6-35B-A3B (upstream base)"
     authors:
       - name: Alibaba Qwen Team
     url: "https://huggingface.co/Qwen/Qwen3.6-35B-A3B"

README.md

@@ -1,7 +1,8 @@
 ---
 license: apache-2.0
 base_model:
-  - Qwen/Qwen3.6-35B-A3B
+  - llmfan46/Qwen3.6-35B-A3B-uncensored-heretic
+base_model_relation: finetune
 datasets:
   - crownelius/Creative_Writing_ShareGPT_Enhanced
   - microsoft/rStar-Coder
@@ -39,6 +40,8 @@ tags:
   - multimodal
   - agent
   - gguf
+  - heretic
+  - uncensored
 library_name: transformers
 pipeline_tag: image-text-to-text
 ---
@@ -46,7 +49,7 @@ pipeline_tag: image-text-to-text
 <img src="https://huggingface.co/FoolDev/Janus-35B/resolve/main/banner.svg" alt="Janus-35B banner" width="100%" />
 
 [![License](https://img.shields.io/badge/License-Apache_2.0-7aa2f7?style=flat&labelColor=1a1b26)](https://opensource.org/licenses/Apache-2.0)
-[![Base Model](https://img.shields.io/badge/Base-Qwen3.6--35B--A3B-bb9af7?style=flat&labelColor=1a1b26)](https://huggingface.co/Qwen/Qwen3.6-35B-A3B)
+[![Base Model](https://img.shields.io/badge/Base-Heretic-bb9af7?style=flat&labelColor=1a1b26)](https://huggingface.co/llmfan46/Qwen3.6-35B-A3B-uncensored-heretic)
 [![Architecture](https://img.shields.io/badge/Arch-MoE_35B/3B_active-ff9e64?style=flat&labelColor=1a1b26)](#architecture)
 [![Quant](https://img.shields.io/badge/GGUF-Q4__K__M-9ece6a?style=flat&labelColor=1a1b26)](#whats-here)
 
@@ -54,12 +57,12 @@ pipeline_tag: image-text-to-text
 
 # Janus-35B
 
-> **Flagship Reasoning. Sparse Footprint.**
-> *Qwen 3.6 35B-A3B repackaged with Claude Fable 5 in the teacher slot.*
+> **Flagship Reasoning. Sparse Footprint. Uncensored.**
+> *llmfan46's Heretic abliteration of Qwen 3.6 35B-A3B, repackaged with Claude Fable 5 in the teacher slot.*
 
-**`Architecture:`** `Qwen 3.6 35B-A3B (MoE)` | **`Total Params:`** `35B` | **`Active Params:`** `3B` | **`Teacher:`** `Claude Fable 5` | **`Type:`** `Distilled MoE LLM`
+**`Architecture:`** `Qwen 3.6 35B-A3B (MoE)` | **`Total Params:`** `35B` | **`Active Params:`** `3B` | **`Base:`** `Heretic (llmfan46)` | **`Teacher:`** `Claude Fable 5` | **`Type:`** `Distilled + Abliterated MoE LLM`
 
-A personal fork of [Qwen/Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B) — a 35B-total / 3B-active mixture-of-experts multimodal model — repackaged as Janus-35B with Claude Fable 5 reasoning data in the teacher slot.
+A personal fork of [`llmfan46/Qwen3.6-35B-A3B-uncensored-heretic`](https://huggingface.co/llmfan46/Qwen3.6-35B-A3B-uncensored-heretic) — an uncensored Heretic-style abliteration of [Qwen/Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B), the 35B-total / 3B-active mixture-of-experts multimodal base — repackaged as Janus-35B with Claude Fable 5 reasoning data in the teacher slot. Refusal-trained behavior is dialed back at the base layer.
 
 ## TL;DR
 
@@ -95,7 +98,14 @@ and `thinking` under Capabilities. Hardware: ~38 GB RAM at default
 | `template`, `system`, `params` | Used by HF's Ollama bridge when users `ollama run hf.co/FoolDev/Janus-35B` directly. The bridge does **not** read `Modelfile` (see [HF Ollama docs](https://huggingface.co/docs/hub/en/ollama)); it ingests these three root-level files instead. Kept in sync with the `Modelfile`'s `TEMPLATE` / `SYSTEM` / `PARAMETER` directives. |
 | `scripts/check_bridge_sync.py` | Run before pushing a `Modelfile` / `template` / `system` / `params` edit to verify the four configurations remain in sync. Exits 0 if in sync, 1 with a per-key diff if not. |
 
-GGUF-only release. Pull the upstream safetensors from `Qwen/Qwen3.6-35B-A3B` if you need the `transformers` tree.
+GGUF-only release. Pull the Heretic safetensors from [`llmfan46/Qwen3.6-35B-A3B-uncensored-heretic`](https://huggingface.co/llmfan46/Qwen3.6-35B-A3B-uncensored-heretic) if you need the `transformers` tree (or the vanilla pre-Heretic base from [`Qwen/Qwen3.6-35B-A3B`](https://huggingface.co/Qwen/Qwen3.6-35B-A3B)).
+
+> **Bundled blob status:** the `Janus-35B-A3B.Q4_K_M.gguf` shipped here is the
+> legacy pre-Heretic Qwen 3.6 35B-A3B quant — it loads and behaves like vanilla
+> Qwen 3.6 35B-A3B for now. A Heretic rebundle (from
+> [`llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-GGUF`](https://huggingface.co/llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-GGUF))
+> is pending; until then, pull a GGUF from that repo directly for the uncensored
+> Heretic behavior.
 
 ## Architecture
 
@@ -316,20 +326,24 @@ print(resp.choices[0].message.tool_calls)
 - **Quantization-induced quality loss.** Q4_K_M is a strong general-purpose quant but does measurably degrade math and code accuracy compared to BF16. If you need maximum quality, run the upstream safetensors on a GPU that fits BF16 (~70 GB).
 - **MoE expert utilization is uneven.** Stock Qwen3.6-35B-A3B routes 8 of 256 experts per token. On narrow domains (e.g. only one programming language) a small subset of experts dominates; load-balance loss was a training-time concern, not a runtime guarantee.
 - **Thinking traces can loop.** Like most reasoning-distilled models, Janus-35B occasionally gets stuck repeating itself inside `<think>` tags. Mitigations: lower temperature to 0.4-0.6, raise `repeat_penalty` to 1.08, or set a `<think>`-token budget cap if your loader supports it.
-- **Not aligned with any specific safety policy.** This is a personal repackage of an open-weight base model with reasoning-focused distillation. There is no RLHF refusal layer beyond what Qwen 3.6 ships with; downstream safety is the operator's responsibility.
+- **Uncensored base — not aligned with any specific safety policy.** This is a personal repackage of an open-weight base whose refusal behavior has been abliterated away (the llmfan46 Heretic base). There is no RLHF refusal layer; the model will attempt most requests, so downstream safety is entirely the operator's responsibility.
 - **No formal evaluation in this card.** Numbers in the hardware table are estimates, not measured. If you produce real benchmarks (MMLU, HumanEval, etc.) and want them included, file a PR.
 
 ## Related models
 
 | Model | Size | Notes |
 |---|---|---|
-| [Qwen/Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B) | 35B / 3B active | Upstream base model. `transformers`-native multimodal weights. |
-| [FoolDev/Thanatos-27B](https://huggingface.co/FoolDev/Thanatos-27B) | 27B dense | Dense sibling on the vanilla [Qwen/Qwen3.6-27B](https://huggingface.co/Qwen/Qwen3.6-27B) base. Same teacher (Fable 5), same dataset family, smaller memory footprint, no MoE quirks. (The old `FoolDev/Thanatos-27B-Heretic` slug now serves a 307 to this path.) |
+| [llmfan46/Qwen3.6-35B-A3B-uncensored-heretic](https://huggingface.co/llmfan46/Qwen3.6-35B-A3B-uncensored-heretic) | 35B / 3B active | **Immediate base.** Uncensored Heretic abliteration of Qwen 3.6 35B-A3B; `transformers`-native safetensors. |
+| [llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-GGUF](https://huggingface.co/llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-GGUF) | 35B / 3B active | Heretic GGUFs — pull one here for the uncensored behavior until the bundled blob is rebundled. |
+| [llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved](https://huggingface.co/llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved) | 35B / 3B active | Same Heretic base but keeps the MTP head for vLLM / SGLang speculative decoding. |
+| [Qwen/Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B) | 35B / 3B active | Upstream pre-Heretic base model. `transformers`-native multimodal weights. |
+| [FoolDev/Thanatos-27B](https://huggingface.co/FoolDev/Thanatos-27B) | 27B dense | Dense sibling on the [`llmfan46/Qwen3.6-27B-uncensored-heretic-v2`](https://huggingface.co/llmfan46/Qwen3.6-27B-uncensored-heretic-v2) Heretic base. Same teacher (Fable 5), same dataset family, smaller memory footprint, no MoE quirks. (The old `FoolDev/Thanatos-27B-Heretic` slug now serves a 307 to this path.) |
 | [Crownelius/Crow-9B-HERETIC-4.6](https://huggingface.co/Crownelius/Crow-9B-HERETIC-4.6) | 9B dense | Heretic-flavored fine-tune of the same Qwen 3.5 9B base used as a smaller starting point. Useful as a fast first-pass model when 35B is too heavy for the host. |
 
 ## Credits
 
-- Base model: [Qwen/Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B) (Alibaba)
+- Immediate base: [llmfan46/Qwen3.6-35B-A3B-uncensored-heretic](https://huggingface.co/llmfan46/Qwen3.6-35B-A3B-uncensored-heretic) — Heretic-style abliteration of Qwen 3.6 35B-A3B
+- Upstream base: [Qwen/Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B) (Alibaba)
 - Reasoning teacher: Claude Fable 5 (Anthropic)
 - Distillation lineage and dataset curation: [Crownelius](https://huggingface.co/Crownelius)