Upload README.md with huggingface_hub

README.md

@@ -42,6 +42,7 @@ Comparison across all tested arms for this model:
 |---|---:|---:|---:|---:|---:|
 | fp16 (reference) | 16.0 | 0.9024 | 0.8598 | 0.8647 | 0.7268 |
 | Unsloth bnb-4bit (competitor) | 4.6919 | 0.9024 | 0.8720 | 0.8596 | 0.7293 |
+| GGUF Q4_K_M (Unsloth, competitor) | 4.8471 | 0.8902 | 0.8293 | 0.8546 | 0.7293 |
 | naive_rowwise_4bit | 4.7594 | 0.8902 | 0.8415 | 0.8521 | 0.7268 |
 | outlier_4bit | 4.7594 | 0.8780 | 0.8293 | 0.8571 | 0.7193 |
 | rotation_outlier_4bit | 4.7784 | 0.9024 | 0.8537 | 0.8521 | 0.7168 |
@@ -50,10 +51,10 @@ Comparison across all tested arms for this model:
 **Honest caveat**: mixed_allocator_4bit does not top every column in this table —
 it matches Unsloth's bnb-4bit exactly on MBPP+Extra (0.7293) and on MBPP Base
 (0.8571 vs 0.8596, essentially tied), but trails on HumanEval relative to
-rotation_outlier_4bit and Unsloth. Its advantage over the other TAQ strategies
-shows more clearly in the fidelity (PPL/KLD) table above than in code-eval
-pass@1, which has higher run-to-run variance at n=164 (HumanEval) / n=399 (MBPP)
-task counts.
+rotation_outlier_4bit, Unsloth, and the real Unsloth GGUF Q4_K_M quant. Its
+advantage over the other TAQ strategies shows more clearly in the fidelity
+(PPL/KLD) table above than in code-eval pass@1, which has higher run-to-run
+variance at n=164 (HumanEval) / n=399 (MBPP) task counts.
 
 ## Provenance