An adversarial audit of today's 0.9.11 and 0.9.12 turned up three defects in the
material they added. All three are fixed here.
1. The trailing-newline explanation was false, and the awk scrape it justified
was never needed. Both releases said "this repo's `template` has no trailing
newline and `ollama show` adds one". `ollama show` adds nothing; the newline
came from the awk in the scrape itself. `ollama show --template <tag>` returns
the template verbatim -- 2570 bytes ending `}`, byte-identical to the file,
cmp-clean. The snippet and the script now use --template and compare directly.
The scrape and the paragraph rationalising it are gone.
2. The check could print "up to date" having compared nothing. `curl -s` is
silent on a DNS failure and exits 0 on a 404, so an unreachable reference plus
an unreadable tag left both sides empty, and equal. Now `curl -fsS`, with an
explicit refusal to compare when either side is empty. 0.9.12 verified only
the match…
Third base change today, and it closes the loop: 0.7.0 restored this MoE, 0.8.0
moved to the dense Qwen 3.8 27B for the newer Qwen generation, 0.9.0 comes back
here. Anyone who pulled on 2026-09-18 may hold either model and should pull again.
Qwen ships no 3.8 at 35B — its 3.8 line is the dense 27B, Flash-Next and
2.4T-A95B — and every Hub model named Qwen3.8-35B-A3B-* is this same 3.6 35B-A3B
with a 3.8 teacher distilled in (empero-ai's Distill and Lord-H4D3ZS's abliterated
Coder variant both declare base_model Qwen/Qwen3.6-35B-A3B). So the choice was 35B
or 3.8, never both. The non-Heretic 3.8 distill was rejected because shipping it
would mean this card could no longer claim an abliterated base.
Restored from tag v0.7.0 rather than rewritten, so what ships is the card that
passed the pre-publish review: MoE architecture bullets asserted against the blob's
own header, moe-routing.svg, the derived KV math, the JANUS-35B artwork, and no
chat_template.jinja (the GGUF carries Qwen 3.6'…
release 0.8.0: back to the dense Qwen 3.8 27B Heretic
0.7.0 reversed the original rebase and shipped the Qwen 3.6 35B-A3B MoE for the
sake of the -35B- slug. 0.8.0 moves back to llmfan46's dense
Qwen3.8-27B-Ultra-Uncensored-Heretic-Native-MTP-Preserved for the newer base
generation. Both moves happened today, so anyone who pulled during 0.7.0 has the
MoE and should re-pull.
There is no Qwen 3.8 at 35B, so this was 35B or 3.8, not both: Qwen's 3.8 line is
the dense 27B, Flash-Next and 2.4T-A95B, and every Hub model named
Qwen3.8-35B-A3B-* is the 3.6 35B-A3B with a 3.8 teacher (both candidates declare
base_model Qwen/Qwen3.6-35B-A3B). llmfan46 ships no 3.8 35B at all.
The dense state is restored from 6708e8f (0.6.5) rather than rewritten, so
chat_template.jinja, its render checks, verify_arch.py's dense expectations, the
REQUIRED MTP strip, the measured memory figures and the 27B artwork all come back
exactly as they were verified. Janus-27B.Q4_K_M.gguf (17,314,193,760 B) is a
pointer-only commit — HF still held the object, so nothing was…
release 0.7.0: reverse the rebase — back to the Qwen 3.6 35B-A3B MoE
Releases 0.2.0 through 0.6.5 shipped a dense Qwen 3.8 27B under this slug.
That rebase is reversed: the model is llmfan46/Qwen3.6-35B-A3B-uncensored-heretic
again — ~34.7B total / ~3B active, 40 layers (10 full-attention + 30 Gated
DeltaNet), 256 experts with 8 routed per token plus a shared expert, arch
qwen35moe. Display name Janus-27B -> Janus-35B, so the Hub slug names the model
correctly again.
- Blob: Janus-35B-A3B.Q4_K_M.gguf restored as a pointer-only commit
(21,233,608,512 B, sha256 b82f9f21…), byte-identical to upstream's Q4_K_M and
to what this repo shipped until da34705. HF still holds that LFS object for
this repo, so nothing is re-uploaded. No re-quantization, no MTP strip (this
quant has no NextN block), no template restamp.
- chat_template.jinja is deleted: it was a patch of the dense base's 3.8
template, and Qwen 3.6's own template — which the GGUF carries — has no
reasoning_effort, tool_call_format or preserve_reasoning to patch. The card's
llama.cpp se…
docs: LM Studio engine tested, loader claims narrowed, make help
- LM Studio's CPU runtime (llama.cpp b10519) passed the same 25 llama-server
checks on both published blobs. The LM Studio app itself could not be kept
off the GPU (it loaded the model with a newer CPU runtime that opened the
GPU), so its API layer stays untested; both guarded attempts were stopped
and every LM Studio file restored.
- The card no longer promises tool calls in Jan, KoboldCpp or llama-cpp-python.
- Janus: --chat-template auto removed (llama.cpp has no such mode).
- make help describes what make check runs.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015DUJPW1e74y1meH5UePzvU
release 0.3.1: JSON tool definitions on Ollama, safer live checks, doc fixes
- Go template renders tool signatures with {{ json .Function }}. Since Ollama
0.14.0 a bare {{ .Function }} printed Go struct syntax inside <tools> (rendered
with Ollama's own template package at v0.33.3; unchanged in 0.34.0 and main).
check 9 now fails on a bare {{ .Function }}. Template-only: no new GGUF.
- live_check.sh: each run uses a fresh subdirectory of WORK_DIR and deletes only
that (it used to delete WORK_DIR itself); transport errors are recorded as
failures instead of aborting; relative GGUF paths work; a server that fails
to start is reported; paths reach Python as arguments. It runs 17 checks.
- check_go_template.py accepts the documented replay-all edit and checks the
think block by nesting, not offset; make live-check honours GGUF_PATH.
- Verified on Ollama 0.34.0 (17/17 on both models). Docs fixes from an
adversarial review: the provenance note no longer credits the upstream base
with the Teacher field and datasets; check counts, llama.cpp and Ollama
…
release 0.3.0: effort line on Ollama, no reasoning replay on llama-server
- Go template reads Ollama's think level and adds the reasoning-effort line
chat_template.jinja adds: high/xhigh/max/ultra -> xhigh, low/minimal -> low,
medium and unset -> none. Verified live on Ollama 0.33.3 (live_check.sh).
- chat_template.jinja ignores preserve_thinking / preserve_reasoning. Recent
llama-server builds set preserve_thinking=true by default, so the old opt-in
replayed every earlier turn's reasoning on a stock server. The bundled GGUF is
restamped in a separate commit.
- check.sh check 9 (check_go_template.py) guards Ollama's thinking detection and
Qwen's stock condition; scripts/live_check.sh (make live-check) runs live
checks in an isolated Ollama.
- Docs: standalone llama.cpp results (master a2878d3 and b10760: one call per
tool request, effort values forwarded), Ollama live results, CPU-only
throughput, and the kwargs-equivalence claim narrowed to the tool-call fix.
- CHANGELOG 0.3.0, CITATION.cff 0.3.0.
Co-Authored-By: Claude Opus 5 (1M context…
feat(scripts): add check.sh, install-hooks.sh and a Makefile
This repo absorbed a full base-model rebase with no automated checks at
all — which is how a Modelfile whose FROM path points at a file not in the
repo shipped unnoticed. The sibling has had check.sh the whole time.
Ports check.sh (bash -n + shellcheck over every shell script, py_compile
over every Python file, the silent-exit footgun grep, and the Modelfile
<-> bridge-file sync check), install-hooks.sh, and a Makefile adapted to
this repo's script set and the `janus` default tag.
The sibling's dot-vs-dash filename guard is deliberately NOT ported: it is
inverted here. mradermacher names heretic-ara quants with a dot, so
Thanatos bans the dash form; llmfan46 names these quants WITH dashes, so
that check would fire on correct filenames. Guard 5 instead blocks a
FROM / BUNDLE= / GGUF= path pointing at an unstripped -MTP-Preserved-
quant — this repo's real footgun, since the base keeps its MTP head and
stock llama.cpp and Ollama cannot load it.
rename_arch.py and heal_hf_pull.sh are no…
