Hugging Face's logo

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

Text Generation
GGUF
English
ggml
llama3
Inference Endpoints
conversational
Model card Files Community
3
leafspark commited on
Commit
dd1a343
·
verified ·
1 Parent(s): 8a4a6cc

readme: fix imatrix info

Browse files
Files changed (1) hide show
  1. README.md +7 -3
README.md CHANGED
@@ -1,6 +1,10 @@
1
  ---
2
  license: llama3.1
3
- library_name: ggml
 
 
 
 
4
  ---
5
 
6
  # Meta-Llama-3.1-405B-Instruct-GGUF
@@ -19,6 +23,6 @@ Low bit quantizations of Meta's Llama 3.1 405B Instruct model. Quantized from ol
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`
 
1
  ---
2
  license: llama3.1
3
+ tags:
4
+ - gguf
5
+ - llama3
6
+ - llama
7
+ pipeline_tag: text-generation
8
  ---
9
 
10
  # Meta-Llama-3.1-405B-Instruct-GGUF
 
23
 
24
  ## imatrix
25
 
26
+ Generated from Q2_K quant.
27
 
28
+ imatrix calibration data: `groups_merged.txt`