Upload llama-3.1-70b-instruct-q6_k-00002-of-00002.gguf

Rename llama-3.1-instruct-70b.imatrix to llama-3.1-70b-instruct.imatrix

Upload llama-3.1-70b-instruct-q6_k-00001-of-00002.gguf

Upload llama-3.1-70b-instruct-q8_0-00002-of-00002.gguf

Upload llama-3.1-70b-instruct-q8_0-00001-of-00002.gguf

Upload llama-3.1-70b-instruct-f16-00003-of-00003.gguf

Upload llama-3.1-70b-instruct-f16-00002-of-00003.gguf

Upload llama-3.1-70b-instruct-f16-00001-of-00003.gguf

Upload importance matrix (2 chunks at 100k tokens)

Upload llama-3.1-70b-instruct-iq2_s.gguf

Upload heavily quantized models

Upload llama-3.1-70b-instruct-q5_0.gguf

Upload llama-3.1-70b-instruct-q4_k.gguf

Upload llama-3.1-70b-instruct-q3_k.gguf

Upload llama-3.1-70b-instruct-q2_k.gguf

initial commit