Upload IQ2_KL and add perplexity values

README.md

@@ -59,57 +59,26 @@ Final estimate: PPL = 4.7056 +/- 0.02909
 <summary>👈 Secret Recipe</summary>
 
 ```bash
-#!/usr/bin/env bash
-
-custom="
-# 47 Repeating Layers [0-46]
-# Note: All ffn_down.* layers are not divisible by 256 so have limited quantization options.
-
-# Attention
-blk\.(0|1)\.attn_q.*=q8_0
-blk\.(0|1)\.attn_k.*=q8_0
-blk\.(0|1)\.attn_v.*=q8_0
-blk\.(0|1)\.attn_output.*=q8_0
-
-blk\..*\.attn_q.*=iq5_ks
-blk\..*\.attn_k.*=iq5_ks
-blk\..*\.attn_v.*=iq5_ks
-blk\..*\.attn_output.*=iq5_ks
-
-# First 1 Dense Layers [0]
-blk\..*\.ffn_down\.weight=q6_0
-blk\..*\.ffn_(gate|up)\.weight=iq5_ks
-
-# Shared Expert Layers [1-46]
-blk\..*\.ffn_down_shexp\.weight=q6_0
-blk\..*\.ffn_(gate|up)_shexp\.weight=iq5_ks
-
-# Routed Experts Layers [1-46]
-blk\..*\.ffn_down_exps\.weight=iq4_nl
-blk\..*\.ffn_(gate|up)_exps\.weight=iq4_kss
-
-# Non-Repeating Layers
-token_embd\.weight=iq4_k
-output\.weight=iq6_k
-"
-
-custom=$(
-  echo "$custom" | grep -v '^#' | \
-  sed -Ez 's:\n+:,:g;s:,$::;s:^,::'
-)
-
-numactl -N 0 -m 0 \
-./build/bin/llama-quantize \
-    --custom-q "$custom" \
-    --imatrix /mnt/raid/models/ubergarm/GLM-4.5-Air-GGUF/imatrix-GLM-4.5-Air-BF16.dat \
-    /mnt/raid/models/ubergarm/GLM-4.5-Air-GGUF/GLM-4.5-Air-128x9.4B-BF16-00001-of-00005.gguf \
-    /mnt/raid/models/ubergarm/GLM-4.5-Air-GGUF/GLM-4.5-Air-IQ4_KSS.gguf \
-    IQ4_KSS \
-    192
+echo TODO
 ```
 
 </details>
 
+## IQ2_KL 43.870 GiB (3.411 BPW)
+Final estimate: PPL = 5.0697 +/- 0.03166
+
+<details>
+
+<summary>👈 Secret Recipe</summary>
+
+```bash
+echo TODO
+```
+
+</summary>
+
+
+
 ## Quick Start
 If you want to disable thinking, add `/nothink` (correct, no underscore) at the *end* of your prompt.