qwp4w3hyb
/

Llama-3-8B-Instruct-Gradient-1048k-iMat-GGUF

Text Generation

importance matrix

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

qwp4w3hyb commited on May 8

Commit

8a1d55d

•

1 Parent(s): aae9efb

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -15,9 +15,9 @@ license_name: llama3
 # Quant Infos
-## Based on newest(2024/05/03) version
-- Requantized for newer updates quants from 2024/05/03.
 - Updated for latest bpe pre-tokenizer fixes https://github.com/ggerganov/llama.cpp/pull/6920
 - quants done with an importance matrix for improved quantization loss
 - K & IQ quants in basically all variants from Q6_K down to IQ1_S

 # Quant Infos
+## Based on new(2024/05/03) version
+- Requantized for new release from 2024/05/03.
 - Updated for latest bpe pre-tokenizer fixes https://github.com/ggerganov/llama.cpp/pull/6920
 - quants done with an importance matrix for improved quantization loss
 - K & IQ quants in basically all variants from Q6_K down to IQ1_S