Add Apache-2.0 metadata and safety notice

README.md

@@ -1,11 +1,29 @@
+---
+license: apache-2.0
+base_model: huihui-ai/Huihui-Qwen3.5-9B-Claude-4.6-Opus-abliterated
+tags:
+- quantization
+- int4
+- rht
+- uzu
+library_name: uzu
+---
+
 # Huihui Qwen3.5-9B INT4 (RHT + Group32 RTN)
 
 Experimental uzu/lalamo checkpoint. **RTN only**; YAQA/QAD not applied yet.
 
 ## Base model
-- `huihui-ai/Huihui-Qwen3.5-9B-Claude-4.6-Opus-abliterated`
+- `huihui-ai/Huihui-Qwen3.5-9B-Claude-4.6-Opus-abliterated` (Apache-2.0)
+- upstream `Qwen/Qwen3.5-9B` (Apache-2.0)
 - untied embedding/lm_head, 32 layers, hidden 4096
 
+## Safety notice
+The base model is "abliterated": its refusal behaviour has been removed. This
+checkpoint inherits that behaviour and can produce unsafe content without
+warning. Do not deploy it as a general-purpose assistant. Downstream use is the
+user's responsibility and must comply with the upstream licenses.
+
 ## Quantization
 - Linear: RHT (Hadamard block 32, input_output) + asymmetric INT4 group 32, layout output_input
 - Input embedding: INT4 (output-only RHT)
@@ -19,7 +37,7 @@ Experimental uzu/lalamo checkpoint. **RTN only**; YAQA/QAD not applied yet.
 
 ## uzu usage
 ```bash
-hf download <repo> --local-dir huihui-9b-int4-rht-rtn
+hf download yamahei21/huihui-qwen3.5-9b-int4-rht-rtn --local-dir huihui-9b-int4-rht-rtn
 uzu cli --model huihui-9b-int4-rht-rtn -m "Say hi in one word."
 ```
 
@@ -31,7 +49,7 @@ uzu cli --model huihui-9b-int4-rht-rtn -m "Say hi in one word."
 - Experimental. Not instruction-tuned after quantization.
 - No YAQA/QAD yet.
 - JA output has factual errors from the base model, not necessarily quantization.
-- License follows the base model and Qwen3.5 terms.
+- License: Apache-2.0, inherited from the base model. See `LICENSE`.
 
 ## Provenance
 See `provenance.json`.