Sync README, CHANGELOG, transformers example with config.json drop

5302d10 removed config.json (to suppress HF's qwen3_5 auto-tag) but
left three docs claiming it was still present:
- README "What's here" table listed config.json
- README transformers paragraph claimed from_pretrained works directly
- examples/transformers_quickstart.py loaded MODEL_ID with no config

Update README table + transformers note to explain the drop and show
a two-step load (AutoConfig from upstream Qwen/Qwen3.6-27B, weights
from this repo — tensors are byte-identical). Switch the example to
match. Add a CHANGELOG entry under Unreleased.

CHANGELOG.md

@@ -7,23 +7,41 @@ and documentation**, not the underlying base model.
 
 ## [Unreleased]
 
+### Removed (transformers config)
+- **Dropped `config.json`** (`5302d10`) to suppress HF's tag
+  auto-detector surfacing `qwen3_5` in the repo header — the
+  detector reads `architectures` from `config.json` and the
+  surfaced tag was obscuring this card's positioning.
+  Consequence: `AutoModelForCausalLM.from_pretrained(
+  "FoolDev/Thanatos-27B")` no longer works on its own.
+  `examples/transformers_quickstart.py` now pulls `AutoConfig`
+  from upstream `Qwen/Qwen3.6-27B` (byte-identical tensors,
+  so no behavioural difference) and weights + tokenizer +
+  chat template from this repo. README's "What's here"
+  table and transformers paragraph updated to match.
+
 ### Added (safetensors mirror)
 - **Mirrored Qwen/Qwen3.6-27B's transformers-loadable safetensors
   set into this repo.** 15 sharded `.safetensors` files (~58 GB
   total) + `model.safetensors.index.json` + tokenizer files
   (`tokenizer.json`, `tokenizer_config.json`, `vocab.json`,
-  `merges.txt`) + configs (`config.json`, `configuration.json`,
+  `merges.txt`) + configs (`configuration.json`,
   `generation_config.json`, `preprocessor_config.json`,
   `video_preprocessor_config.json`) + `chat_template.jinja`.
-  Tensor data byte-identical to upstream; the mirror saves a
-  second `hf download` for users who want both GGUF + safetensors
-  in one place. `.gitignore` was updated separately (commit
+  (`config.json` was initially mirrored too, then dropped — see
+  "Removed (transformers config)" above.) Tensor data
+  byte-identical to upstream; the mirror saves a second
+  `hf download` for users who want both GGUF + safetensors in
+  one place. `.gitignore` was updated separately (commit
   `0c5bee4`) to whitelist the Qwen sharded naming pattern before
   the upload's preupload check ran (HF reads the destination
   repo's `.gitignore` to decide `shouldIgnore` per file).
-- `examples/transformers_quickstart.py` now defaults `MODEL_ID`
-  to `FoolDev/Thanatos-27B` so a fresh user only needs to pull
-  this repo to get a working transformers entry point.
+- `examples/transformers_quickstart.py` defaults `MODEL_ID`
+  to `FoolDev/Thanatos-27B` (weights + tokenizer + chat
+  template) with `CONFIG_ID="Qwen/Qwen3.6-27B"` for the
+  architecture config — fresh users still need only this
+  repo as the entry point, with one auxiliary HF Hub pull
+  for `config.json` that transformers handles transparently.
 
 ### Changed (5th round trip — qwen36 → qwen35, retested next-day)
 - **Bundle re-stamped `general.architecture: 'qwen36'` → `'qwen35'`**

README.md

@@ -126,7 +126,7 @@ The 27B is **dense**: every parameter participates in every forward pass. It's s
 | `scripts/install-hooks.sh` | Installs `check.sh` as a git pre-commit hook |
 | `Makefile` | Convenience wrapper — `make help` lists targets |
 | `model-*-of-00015.safetensors` (15 files, ~58 GB) + `model.safetensors.index.json` | Transformers-loadable safetensors mirror of `Qwen/Qwen3.6-27B`. Byte-identical to upstream. |
-| `config.json`, `configuration.json`, `generation_config.json`, `preprocessor_config.json`, `video_preprocessor_config.json`, `chat_template.jinja` | Model + processor + chat-template configs mirrored from upstream — what `from_pretrained` needs. |
+| `configuration.json`, `generation_config.json`, `preprocessor_config.json`, `video_preprocessor_config.json`, `chat_template.jinja` | Processor + chat-template configs mirrored from upstream. **`config.json` is intentionally not in this repo** — HF's tag auto-detector reads `architectures` from it and surfaces `qwen3_5` in the repo header, which obscures this repo's positioning. Transformers users: pull `config.json` from [`Qwen/Qwen3.6-27B`](https://huggingface.co/Qwen/Qwen3.6-27B) (see Transformers note below). |
 | `tokenizer.json`, `tokenizer_config.json`, `vocab.json`, `merges.txt` | Tokenizer files mirrored from upstream. |
 | `LICENSE`, `CITATION.cff` | Apache-2.0 license and citation metadata |
 | `CHANGELOG.md` | Versioned tooling/docs changes |
@@ -142,13 +142,27 @@ path applies the root-level `template`, `system`, and `params`
 files (kept in sync with the `Modelfile`).
 
 The transformers safetensors set is mirrored in this repo
-(15 sharded `.safetensors` files + index + tokenizer + configs
-+ chat template), so `AutoModelForCausalLM.from_pretrained(
-"FoolDev/Thanatos-27B")` works directly. Tensor data is
-byte-identical to upstream [`Qwen/Qwen3.6-27B`](https://huggingface.co/Qwen/Qwen3.6-27B);
-the mirror exists so consumers don't need a second pull from
-two repos to assemble the full toolkit (GGUF + safetensors +
-mmproj reference).
+(15 sharded `.safetensors` files + index + tokenizer +
+chat template), byte-identical to upstream
+[`Qwen/Qwen3.6-27B`](https://huggingface.co/Qwen/Qwen3.6-27B).
+**`config.json` is not bundled here** — HF auto-detects model
+architecture from it and surfaces a `qwen3_5` repo-level tag
+that obscures this card. To load via transformers, either:
+
+```python
+# A. Use upstream as the config/architecture source, this repo for weights:
+from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer
+cfg = AutoConfig.from_pretrained("Qwen/Qwen3.6-27B", trust_remote_code=True)
+tok = AutoTokenizer.from_pretrained("FoolDev/Thanatos-27B", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    "FoolDev/Thanatos-27B", config=cfg, trust_remote_code=True,
+)
+
+# B. Or just load upstream directly — tensors are byte-identical:
+model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.6-27B", trust_remote_code=True)
+```
+
+`examples/transformers_quickstart.py` uses path A.
 
 ## Architecture
 

examples/transformers_quickstart.py

@@ -7,9 +7,12 @@ mirror of Qwen/Qwen3.6-27B's transformers set) and runs a single
 chat turn using its embedded chat template. Applies the same
 Thanatos system prompt the Modelfile / bridge `system` file uses.
 
-`MODEL_ID` defaults to "FoolDev/Thanatos-27B" so the safetensors and
-chat template come from this repo in one pull; flip it back to
-"Qwen/Qwen3.6-27B" to source directly from upstream.
+`config.json` is intentionally not in this repo (it makes HF's tag
+auto-detector surface a `qwen3_5` repo-level tag), so we source the
+architecture config from upstream `Qwen/Qwen3.6-27B` and only pull
+weights + tokenizer + chat template from this repo. Tensor data is
+byte-identical, so the result is the same model. Set
+`MODEL_ID = "Qwen/Qwen3.6-27B"` to bypass this repo entirely.
 
 Requirements:
     pip install --upgrade "transformers>=4.45" accelerate sentencepiece bitsandbytes
@@ -31,7 +34,7 @@ import sys
 
 try:
     import torch
-    from transformers import AutoModelForCausalLM, AutoTokenizer
+    from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer
 except ImportError as e:  # pragma: no cover
     sys.exit(
         f"Missing dependency: {e.name}. Install with:\n"
@@ -40,6 +43,7 @@ except ImportError as e:  # pragma: no cover
 
 
 MODEL_ID = "FoolDev/Thanatos-27B"
+CONFIG_ID = "Qwen/Qwen3.6-27B"  # source of config.json (not bundled in MODEL_ID — see module docstring)
 
 THANATOS_SYSTEM = (
     "You are Thanatos, a precise and capable assistant for reasoning, writing, "
@@ -71,8 +75,11 @@ def load(use_4bit: bool):
         )
         kwargs.pop("torch_dtype", None)
 
+    cfg = AutoConfig.from_pretrained(CONFIG_ID, trust_remote_code=True)
     tok = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True)
-    model = AutoModelForCausalLM.from_pretrained(MODEL_ID, trust_remote_code=True, **kwargs)
+    model = AutoModelForCausalLM.from_pretrained(
+        MODEL_ID, config=cfg, trust_remote_code=True, **kwargs,
+    )
     return tok, model