{ "dfloat11_config": { "version": "0.5.0", "threads_per_block": [ 512 ], "bytes_per_thread": 8, "pattern_dict": { "lm_head": [], "model\\.language_model\\.embed_tokens": [], "model\\.language_model\\.layers\\.\\d+": [ "self_attn.q_proj", "self_attn.k_proj", "self_attn.v_proj", "self_attn.o_proj", "mlp.gate_proj", "mlp.up_proj", "mlp.down_proj" ], "model\\.visual\\.blocks\\.\\d+": [ "attn.qkv", "attn.proj", "mlp.gate_proj", "mlp.up_proj", "mlp.down_proj" ], "model\\.visual\\.merger\\.mlp": [ "0", "2" ] } } }