Update README.md

Add GGUF internal file structure

Generate Perplexity, KLD, ARC, HellaSwag, MMLU, Truthful QA and WinoGrande scores

Regenerate imatrices

Layer-wise quantization IQ3_S

Regenerate base model logits

Layer-wise quantization IQ3_M

Layer-wise quantization IQ4_NL

Layer-wise quantization Q3_K_S

Layer-wise quantization Q3_K_L

Layer-wise quantization Q3_K_M

Layer-wise quantization Q4_K_M

Layer-wise quantization Q4_K_S

Layer-wise quantization Q5_K_M

Layer-wise quantization Q5_K_S

Layer-wise quantization Q6_K

Layer-wise quantization Q8_0

Update README.md

Update README.md

Update README.md

Add README.md

Generate perplexity and kld scores

Generate IQ3_M quant

Generate IQ3_S quant

Generate IQ4_NL quant

Generate Q3_K_L quant

Generate Q3_K_M quant

Generate Q4_K_S quant

Generate Q5_K_M quant

Generate Q5_K_S quant

Generate Q6_K quant

Generate Q8_0 quant

Generate Small imatrix

Generate Tiny imatrix

Generate Micro imatrix

Generate base model logits

Convert to GGUF @ F16

Update .gitignore

Update .gitattributes

initial commit