Hugging Face's logo

AesSedai
/
GLM-4.7-GGUF

GGUF
imatrix
conversational
Model card Files
xet
Community
AesSedai commited on
Commit
9bd4fc6
·
verified ·
1 Parent(s): 8045c32

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -1
README.md CHANGED
@@ -19,4 +19,8 @@ I've mapped these mixes to the closest BPW I could reasonably discern.
19
  | IQ4_XS | 165.28 GiB (3.96 BPW) | Q8_0-IQ3_S-IQ3_S-IQ4_XS | 8.8664 ± 0.16071 | 0.04375 ± 0.00107 |
20
  | IQ2_M | 107.12 GiB (2.57 BPW) | Q5_K-IQ2_XXS-IQ2_XXS-IQ3_XXS | 9.8248 ± 0.17931 | 0.19464 ± 0.00315 |
21
 
22
- ![ppl_ratio_vs_kld](ppl_ratio_vs_kld.png "Chart showing PPL vs KLD analysis of quants")
 
 
 
 
 
19
  | IQ4_XS | 165.28 GiB (3.96 BPW) | Q8_0-IQ3_S-IQ3_S-IQ4_XS | 8.8664 ± 0.16071 | 0.04375 ± 0.00107 |
20
  | IQ2_M | 107.12 GiB (2.57 BPW) | Q5_K-IQ2_XXS-IQ2_XXS-IQ3_XXS | 9.8248 ± 0.17931 | 0.19464 ± 0.00315 |
21
 
22
+ ![ppl_ratio_vs_kld](ppl_ratio_vs_kld.png "Chart showing PPL vs KLD analysis of quants")
23
+
24
+ ## Shout Outs
25
+ * [Bartowski's imatrix_v3 corpus](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
26
+ * [Ubergarm's ik_llama quants (for SOTA quant schemas)](https://huggingface.co/ubergarm/GLM-4.7-GGUF)