MarsupialAI
/

Llama3_GGUF_Quant_Testing

Model card Files Files and versions Community

MarsupialAI commited on Apr 25

Commit

21d3cb1

•

1 Parent(s): 5e8baaa

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -9,7 +9,7 @@ So to test this crazy theory, I downloaded Undi95/Meta-Llama-3-8B-Instruct-hf an
 - fp32 specifically with `--outtype f32`
 - "Auto" with no outtype specified
-I then quantized each of these conversions to Q4_K_M and ran perplexity tests on everything using my abbreviated wiki.short.raw
 The results:

 - fp32 specifically with `--outtype f32`
 - "Auto" with no outtype specified
+I then quantized each of these conversions to Q4_K_M and ran perplexity tests on everything using my abbreviated wiki.short.raw text file
 The results: