Fable-Fusion-711 27B — bf16 (reconstructed safetensors)
Explore the model guide · All public work
Release at a glance
| This artifact |
|---|
| Purpose | A BF16 tensor reconstruction from the released Q8_0 GGUF, useful for inspecting or building further conversions. |
| Runtime | Reconstruction in a Hugging Face tensor layout. It is a conversion source, not an independently qualified serving stack for every listed framework. |
| Status | Reference build; see the evidence and limits below. |
| Tensor download | 55.56 GB (51.75 GiB) of root .safetensors files, including any root sidecars. This is a file-size total, not peak RAM. |
| Read first | BF16 describes the stored dtype. It cannot recover precision lost in Q8_0 and is not the original training checkpoint. |
A BF16 reconstruction from DavidAU's Q8_0 MTP GGUF. BF16 is the
storage dtype; reconstruction does not recover precision lost during Q8_0
quantization. The artifact includes: language model, MTP head, and
vision tower, in standard Qwen3_5ForConditionalGeneration form.
56 GB.
Behavioral correction — July 26, 2026
This reconstruction faithfully reproduces the released Fable-Fusion weights,
but those weights do not reproduce the source card's 4/100 refusal claim.
On the exact Heretic KeywordRate protocol (same 100 prompts, system prompt,
100-token cap, and 37 substring markers), official Qwen scored 99/100,
DavidAU's released Q6_K scored 81/100, and the converted tune scored
79/100. All outputs were non-empty.
KeywordRate is a refusal-marker proxy, not a semantic compliance judge.
Accordingly, this repository is no longer described or tagged as uncensored.
For the later official-Qwen reduced-refusal artifact, see
Qwen3.6-27B-Refusal-Ablation-v2-MTPLX-6bit.
Intended as an input to further quantization or runtime integration. A
standard tensor layout alone does not qualify Transformers, vLLM, EXL, AWQ,
or GPTQ execution; verify the exact architecture and loader before use. Perplexity 5.7525 (wikitext-2, ctx 2048); DavidAU's
Q8_0 GGUF measures 5.6635 under llama.cpp's own methodology.
Honest provenance: this is a dequantization of Q8_0, not the original training
checkpoint — Q8_0 is near-lossless but not lossless. If DavidAU ever publishes
the true bf16, prefer it.
Ready-made quants of this:
MTPLX 6-bit ·
MTPLX 8-bit ·
MTPLX 4-bit.
How this was made (and the traps if you try it)
DavidAU published GGUF only, so this was reconstructed from his highest-precision
export — the Q8_0 MTP GGUF — by inverting every transform llama.cpp applies
when it converts Qwen3.5/3.6. Get any of these wrong and the model degenerates
while still passing consistency-style checks:
- Zero-centered RMSNorm baking. GGUF stores these norms as
weight + 1:
input/post-attention layernorms, q/k norms, the final norm, and all mtp.*
norms (nextn.enorm / hnorm / shared_head_norm). mlx-lm's qwen3_5
sanitize adds +1 itself, so a naive conversion double-shifts. Gated
linear_attn.norm and the vision norms are NOT baked.
- Gated-DeltaNet value-head reorder (
_LinearAttentionVReorderBase in
llama.cpp's conversion/qwen.py). V heads move from HF grouped order to
ggml tiled order in in_proj_qkv (V rows), in_proj_z, in_proj_a,
in_proj_b, A_log, dt_bias, conv1d (V channels), and out_proj
(columns, not rows). Note the first V head occupies the same offset in
both orderings — spot-checks at offset 0 are blind to this bug.
ssm_a = -exp(A_log) — recover with log(-x), then apply the reorder.
MTP head mapping: blk.<last>.nextn.{eh_proj,enorm,hnorm,shared_head_norm} →
mtp.{fc,pre_fc_norm_embedding,pre_fc_norm_hidden,norm}, and the final block's
attention/MLP → mtp.layers.0.*.
Every tensor was shape-checked against Qwen/Qwen3.6-27B and the layout
verified by cosine similarity against base values (a finetune leaves many
tensors at or near base, so a residual permutation shows up as ~0 correlation).
All families landed at 0.99–1.0000 after inversion.
Independently validated. After these builds were published, an F32 copy of
the same tune surfaced:
nightmedia/Qwen3.6-27B-Architect-Polaris2-Fable-B-F451-F32
(112 GB, mergekit
nuslerp). It has the identical structure — 1199 tensors,
15
mtp.*, 333 vision — and this reconstruction matches it at
cosine 0.99997
on
mtp.fc.weight and
1.00000 on
model.language_model.norm.weight. The
residual is precisely the Q8_0 step this copy came through, so the inverse
transforms above are confirmed correct against a source never used to derive them.
If you want the highest-fidelity starting point for your own quants, prefer that
F32 repo over this reconstruction — it never passed through a quantizer.
Credits and license
- DavidAU — the Fable-Fusion-711 tune and
the Q8_0 MTP export this is reconstructed from. Please read
his model card for the tune's
capabilities, sampler guidance, and class notes.
- Qwen — Qwen3.6-27B base.
- MTPLX — forge pipeline and MTP runtime.
Apache-2.0, inherited from the source model.
Intended use
Research and creative work. Do not assume this model is refusal-free; deploy
behind your own policy and logging layer.
