Post-audit README fixes + add .gitignore

A read-only 5-dimension audit of the model card surfaced two verified
doc-accuracy defects and one repo-hygiene gap vs the dense sibling.

Fixed (README):
- Hardware section said "18.9 GB" for the bundled Q4_K_M; the file is
~19.8 GB and the rest of the card says "~19 GB" (TL;DR, "What's here"
table, Ollama quick-start). Unified to "~19 GB".
- "Related models" table still told users to pull Heretic GGUFs "until
the bundled blob is rebundled" — but the rebundle is done (commit
b302576; see the "Bundled blob status" callout). Reworded to "pull
other quants here; the bundled Q4_K_M is already this Heretic quant."

Added:
- .gitignore, mirrored from FoolDev/Thanatos-27B-HERETIC and tailored to
Janus (keeps the shipped Janus-35B-A3B.*.gguf; drops the sibling's
rename_arch.py rebadge line, which Janus has no script for). The repo
ships Python scripts that generate __pycache__ and had no ignore file
guarding the public repo against junk / stray-GGUF commits.

CHANGELOG [Unreleased] updated to match. Bridge-sync still passes; the
bundled GGUF is not caught by the new ignore rules.

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

.gitignore

@@ -0,0 +1,29 @@
+# Python
+__pycache__/
+*.py[cod]
+*.egg-info/
+.venv/
+venv/
+
+# Local model weights. We don't redistribute the upstream Qwen GGUFs
+# here — scripts/build.sh fetches one from
+# llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-GGUF locally. The single
+# Janus-35B-A3B.*.gguf we DO ship backs the HF/Ollama "Use this model"
+# widget (ollama run hf.co/FoolDev/Janus-35B-HERETIC).
+*.gguf
+!Janus-35B-A3B.*.gguf
+*.safetensors
+*.bin
+
+# Build / runtime artifacts that get created if anyone runs hf download or
+# scripts/build.sh from inside the repo.
+.cache/
+*.incomplete
+*.lock
+
+# Editor / OS
+.DS_Store
+.idea/
+.vscode/
+*.swp
+*~

CHANGELOG.md

@@ -8,6 +8,25 @@ track the **tooling and documentation**, not the underlying base model.
 
 ## [Unreleased]
 
+### Fixed (post-rebundle README drift)
+- **Hardware section GGUF size `18.9 GB` → `~19 GB`** — matches the actual
+  ~19.8 GB bundled file and the `~19 GB` already used in the TL;DR, the
+  "What's here" table, and the Ollama quick-start.
+- **Dropped the stale "until the bundled blob is rebundled" note** from the
+  Heretic-GGUF row of the "Related models" table. The rebundle is complete
+  (see the base-swap entry below and the "Bundled blob status" callout); the
+  row now reads "pull other quants here; the bundled Q4_K_M is already this
+  Heretic quant."
+
+### Added (repo hygiene)
+- **`.gitignore`** — mirrors the dense sibling `FoolDev/Thanatos-27B-HERETIC`,
+  tailored to Janus: ignores Python caches / venvs, HF / `scripts/build.sh`
+  runtime artifacts (`.cache/`, `*.incomplete`, `*.lock`), and stray weights
+  (`*.gguf` / `*.safetensors` / `*.bin`) while keeping the shipped
+  `Janus-35B-A3B.*.gguf` that backs the "Use this model" widget. Omits the
+  sibling's `scripts/rename_arch.py` rebadge-ignore line (Janus has no such
+  script).
+
 ### Changed (HF repo rename → FoolDev/Janus-35B-HERETIC)
 - **HF repository slug renamed `FoolDev/Janus-35B` → `FoolDev/Janus-35B-HERETIC`.**
   The old slug now 307-redirects to the new one. The model's **display name

README.md

@@ -220,7 +220,7 @@ Behavior rules:
 
 ## Hardware requirements
 
-This is an 18.9 GB Q4_K_M GGUF. Ollama's runtime footprint at default settings is **roughly 2× the model file** (weights mmap + compute graph allocation), plus KV cache — so ~38 GB total memory at `num_ctx 16384`. The compute-graph allocation scales with context and batch size, so 32 GB hosts can fit the model by trimming both (see Z13 row in the table).
+This is a ~19 GB Q4_K_M GGUF. Ollama's runtime footprint at default settings is **roughly 2× the model file** (weights mmap + compute graph allocation), plus KV cache — so ~38 GB total memory at `num_ctx 16384`. The compute-graph allocation scales with context and batch size, so 32 GB hosts can fit the model by trimming both (see Z13 row in the table).
 
 | Hardware | Status |
 |---|---|
@@ -336,7 +336,7 @@ print(resp.choices[0].message.tool_calls)
 | Model | Size | Notes |
 |---|---|---|
 | [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-GGUF](https://huggingface.co/llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-GGUF) | 35B / 3B active | Heretic GGUFs — pull other quants here; the bundled Q4_K_M is already this Heretic quant. |
 | [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-HERETIC](https://huggingface.co/FoolDev/Thanatos-27B-HERETIC) | 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 older `FoolDev/Thanatos-27B` and `Thanatos-27B-Heretic` slugs now 307 to this path.) |