Hugging Face's logo

leafspark
/
Meta-Llama-3.1-405B-Instruct-GGUF

Text Generation
GGUF
English
ggml
llama3
Model card Files Community
3
leafspark commited on
Commit
a29e824
·
verified ·
1 Parent(s): 362d372

readme: fix formatting

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -17,8 +17,8 @@ Low bit quantizations of Meta's Llama 3.1 405B Instruct model. Quantized from ol
17
  - Q4_0
18
  - Q4_K_S
19
 
20
- imatrix calibration data: groups_merged.dat
21
-
22
  ## imatrix
23
 
24
- Experimental, force quanted to iq1_m, then an imatrix is generated and quanted to iq1_m again, and that is used to generate the final imatrix for all quants.
 
 
 
17
  - Q4_0
18
  - Q4_K_S
19
 
 
 
20
  ## imatrix
21
 
22
+ Experimental, force quanted to iq1_m, then an imatrix is generated and quanted to iq1_m again, and that is used to generate the final imatrix for all quants.
23
+
24
+ imatrix calibration data: `groups_merged.dat`