Update README.md

README.md

@@ -67,7 +67,7 @@ custom="
 blk\.0\.ffn_down\.weight=q8_0
 blk\.0\.ffn_gate\.weight=q8_0
 blk\.0\.ffn_up\.weight=q8_0
-blk\.46\.nextn\.eh_proj\.weight=f16
+blk\.46\.nextn\.eh_proj\.weight=bf16
 blk\.46\.nextn\.embed_tokens\.weight=q8_0
 blk\.46\.nextn\.enorm\.weight=f32
 blk\.46\.nextn\.hnorm\.weight=f32
@@ -104,32 +104,32 @@ blk\.4[0-6]\.post_attention_norm\.weight=f32
 
 blk\.[1-9]\.exp_probs_b\.bias=f32
 blk\.[1-9]\.ffn_down_exps\.weight=q8_0
-blk\.[1-9]\.ffn_down_shexp\.weight=f16
+blk\.[1-9]\.ffn_down_shexp\.weight=bf16
 blk\.[1-9]\.ffn_gate_exps\.weight=q4_K
 blk\.[1-9]\.ffn_gate_inp\.weight=f32
-blk\.[1-9]\.ffn_gate_shexp\.weight=f16
+blk\.[1-9]\.ffn_gate_shexp\.weight=bf16
 blk\.[1-9]\.ffn_up_exps\.weight=q4_K
-blk\.[1-9]\.ffn_up_shexp\.weight=f16
+blk\.[1-9]\.ffn_up_shexp\.weight=bf16
 blk\.[1-3][0-9]\.exp_probs_b\.bias=f32
 blk\.[1-3][0-9]\.ffn_down_exps\.weight=q8_0
-blk\.[1-3][0-9]\.ffn_down_shexp\.weight=f16
+blk\.[1-3][0-9]\.ffn_down_shexp\.weight=bf16
 blk\.[1-3][0-9]\.ffn_gate_exps\.weight=q4_K
 blk\.[1-3][0-9]\.ffn_gate_inp\.weight=f32
-blk\.[1-3][0-9]\.ffn_gate_shexp\.weight=f16
+blk\.[1-3][0-9]\.ffn_gate_shexp\.weight=bf16
 blk\.[1-3][0-9]\.ffn_up_exps\.weight=q4_K
-blk\.[1-3][0-9]\.ffn_up_shexp\.weight=f16
+blk\.[1-3][0-9]\.ffn_up_shexp\.weight=bf16
 blk\.4[0-6]\.exp_probs_b\.bias=f32
 blk\.4[0-6]\.ffn_down_exps\.weight=q8_0
-blk\.4[0-6]\.ffn_down_shexp\.weight=f16
+blk\.4[0-6]\.ffn_down_shexp\.weight=bf16
 blk\.4[0-6]\.ffn_gate_exps\.weight=q4_K
 blk\.4[0-6]\.ffn_gate_inp\.weight=f32
-blk\.4[0-6]\.ffn_gate_shexp\.weight=f16
+blk\.4[0-6]\.ffn_gate_shexp\.weight=bf16
 blk\.4[0-6]\.ffn_up_exps\.weight=q4_K
-blk\.4[0-6]\.ffn_up_shexp\.weight=f16
+blk\.4[0-6]\.ffn_up_shexp\.weight=bf16
 
-output\.weight=f16
+output\.weight=bf16
 output_norm\.weight=f32
-token_embd\.weight=f16
+token_embd\.weight=bf16
 "
 
 custom=$(
@@ -143,7 +143,7 @@ TARGET_MODEL="GLM-4.5-Air-HQ4_K"
 mkdir -p ~/Env/models/anikifoss/$TARGET_MODEL
 ./build/bin/llama-quantize \
     --custom-q "$custom" \
-    /mnt/data/Models/zai-org/GLM-4.5-Air-GGUF/GLM-4.5-Air-128x9.4B-F16-00001-of-00005.gguf \
+    /mnt/data/Models/zai-org/GLM-4.5-Air-GGUF/GLM-4.5-Air-128x9.4B-BF16-00001-of-00005.gguf \
     ~/Env/models/anikifoss/$TARGET_MODEL/$TARGET_MODEL.gguf \
     Q4_K \
     32