Hugging Face's logo

InferenceIllusionist
/
WizardLM-2-8x22B-iMat-GGUF

GGUF
Merge
mixtral
iMat
Inference Endpoints
conversational
Model card Files Community
InferenceIllusionist commited on
Commit
b85b1a5
·
verified ·
1 Parent(s): b257e17

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -11,7 +11,7 @@ tags:
11
 
12
 
13
  Quantized from fp32 with love. If you're using the latest version of llama.cpp you should no longer need to combine files before loading.
14
- * Weighted quantizations created using [imatrix file](https://huggingface.co/jukofyork/WizardLM-2-8x22B-imatrix) provided by jukofyork
15
  * Calculated in 105 chunks with n_ctx=512 using groups_merged.txt
16
 
17
  For a brief rundown of iMatrix quant performance please see this [PR](https://github.com/ggerganov/llama.cpp/pull/5747)
 
11
 
12
 
13
  Quantized from fp32 with love. If you're using the latest version of llama.cpp you should no longer need to combine files before loading.
14
+ * Importance matrix calculated using fp16 precision model
15
  * Calculated in 105 chunks with n_ctx=512 using groups_merged.txt
16
 
17
  For a brief rundown of iMatrix quant performance please see this [PR](https://github.com/ggerganov/llama.cpp/pull/5747)