add quantization_config.ignore=['lm_head', 're:.*mlp\\.gate$', 're:.*linear_attn\\.in_proj_a$', 're:.*linear_attn\\.in_proj_b$', 're:.*shared_expert\\..*']

add vocab.json

add tokenizer_config.json

add tokenizer.json

add special_tokens_map.json

add model.safetensors.index.json

add model-00008-of-00008.safetensors

add model-00007-of-00008.safetensors

add model-00006-of-00008.safetensors

add model-00005-of-00008.safetensors

add model-00004-of-00008.safetensors

add model-00003-of-00008.safetensors

add model-00002-of-00008.safetensors

add model-00001-of-00008.safetensors

add merges.txt

add generation_config.json

add config.json

add chat_template.jinja

add added_tokens.json

initial commit