docs: model card TLDR, family table, red-team intended use, CLI unify

README.md

@@ -25,6 +25,29 @@ subset of them. Load, quantize, and serve it exactly like the base model.
 
 ---
 
+## Intended use: red teaming and defensive cybersecurity research
+
+These uncensored (abliterated) weights are built as a **research instrument** for red teaming and defensive cybersecurity work. Safety training suppresses the *display* of capability, not capability itself. A refusal tells you the model declined. It does not tell you whether the weights could have complied. That conflation underestimates the true ceiling and hides holes in *your* filters, classifiers, and policy layer.
+
+Use each uncensored checkpoint as the **treatment half of a controlled pair** against its original base model:
+
+- **Capability-ceiling measurement.** Upper-bound what the weights can actually produce in a domain, independent of shipped refusals.
+- **Defensive-stack evaluation.** Test input filters, output classifiers, prompt-injection defenses, and moderation APIs when the model itself contributes no refusals. That is how you find gaps in a defensive control plane.
+- **Attack-surface isolation.** Automated red-team loops stall on unrelated refusals. A non-refusing target isolates the control under test (injection, tool abuse, data-exfil paths, policy bypass).
+- **Detection and classifier work.** Generate labeled completions for training or benchmarking output-moderation and abuse-detection models.
+- **Interpretability of residual refusal.** Abliteration is a specified rank-1 edit on a known layer span. The pair (base vs this) is a clean experimental control.
+
+**Operating rules.** Do not expose these weights as a public endpoint without an independent moderation layer. Abliteration removes a direction, not a policy; some refusals survive (multi-turn re-assertion, system-prompt steering, vision-path refusals). Always report the **delta against the base model**. Re-measure on your own prompts. Whoever deploys it owns the moderation layer the original guardrails were carrying.
+
+## Family
+
+| Repo | Format | What it is |
+|---|---|---|
+| [Qwen-3.8-27B-Uncensored](https://huggingface.co/junafinity/Qwen-3.8-27B-Uncensored) | bf16, `transformers` | Full multimodal parent (~52 GB). Vision + `mtp.*` retained. |
+| [Qwen-3.8-27B-Uncensored-8-Bit-MLX](https://huggingface.co/junafinity/Qwen-3.8-27B-Uncensored-8-Bit-MLX) | 8-bit MLX, `mlx-vlm` | Apple Silicon quant (~28 GB). Vision left at bf16. `mtp.*` dropped by `mlx-vlm`. |
+| [qwen38-mtp-head-fc-bf16-4bit](https://huggingface.co/junafinity/qwen38-mtp-head-fc-bf16-4bit) | mixed bf16 `fc` + 4-bit/g64 | Optional native-MTP draft head. Pairing is optional and **acceptance gain is unmeasured** on hard prompts. |
+
+
 ## Attribution
 
 This model is derivative work built on the efforts of two upstream projects.
@@ -367,15 +390,11 @@ Read these before relying on the model.
 
 ## Intended use
 
-Refusal-mechanism and interpretability research, red-teaming and safety evaluation (see
-[Red teaming and safety research](#red-teaming-and-safety-research)), and deployments where the
-operator supplies their own content policy and moderation layer.
+Primary intended use is **red teaming and defensive cybersecurity research**. See [Intended use: red teaming and defensive cybersecurity research](#intended-use-red-teaming-and-defensive-cybersecurity-research) above.
 
-Users are responsible for compliance with applicable law and with the Apache 2.0 terms inherited from
-the base model. This model ships without the guardrails Qwen trained into it; anyone deploying it
-takes on the moderation responsibility those guardrails were carrying.
+Also: refusal-mechanism / interpretability research, and deployments where the operator supplies an independent content-policy and moderation layer.
 
----
+Users are responsible for compliance with applicable law and with the Apache 2.0 terms inherited from the base model. This model ships without the guardrails Qwen trained into it.
 
 ## License