{ "component": "text_encoder", "method": "bitsandbytes LLM.int8", "threshold": 6.0, "skip_modules": [ "lm_head", "visual", "model.visual" ], "linear8bit_modules": [ "model.language_model.layers.0.self_attn.q_proj", "model.language_model.layers.0.self_attn.k_proj", "model.language_model.layers.0.self_attn.v_proj", "model.language_model.layers.0.self_attn.o_proj", "model.language_model.layers.0.mlp.gate_proj", "model.language_model.layers.0.mlp.up_proj", "model.language_model.layers.0.mlp.down_proj", "model.language_model.layers.1.self_attn.q_proj", "model.language_model.layers.1.self_attn.k_proj", "model.language_model.layers.1.self_attn.v_proj", "model.language_model.layers.1.self_attn.o_proj", "model.language_model.layers.1.mlp.gate_proj", "model.language_model.layers.1.mlp.up_proj", "model.language_model.layers.1.mlp.down_proj", "model.language_model.layers.2.self_attn.q_proj", "model.language_model.layers.2.self_attn.k_proj", "model.language_model.layers.2.self_attn.v_proj", "model.language_model.layers.2.self_attn.o_proj", "model.language_model.layers.2.mlp.gate_proj", "model.language_model.layers.2.mlp.up_proj", "model.language_model.layers.2.mlp.down_proj", "model.language_model.layers.3.self_attn.q_proj", "model.language_model.layers.3.self_attn.k_proj", "model.language_model.layers.3.self_attn.v_proj", "model.language_model.layers.3.self_attn.o_proj", "model.language_model.layers.3.mlp.gate_proj", "model.language_model.layers.3.mlp.up_proj", "model.language_model.layers.3.mlp.down_proj", "model.language_model.layers.4.self_attn.q_proj", "model.language_model.layers.4.self_attn.k_proj", "model.language_model.layers.4.self_attn.v_proj", "model.language_model.layers.4.self_attn.o_proj", "model.language_model.layers.4.mlp.gate_proj", "model.language_model.layers.4.mlp.up_proj", "model.language_model.layers.4.mlp.down_proj", "model.language_model.layers.5.self_attn.q_proj", "model.language_model.layers.5.self_attn.k_proj", "model.language_model.layers.5.self_attn.v_proj", "model.language_model.layers.5.self_attn.o_proj", "model.language_model.layers.5.mlp.gate_proj", "model.language_model.layers.5.mlp.up_proj", "model.language_model.layers.5.mlp.down_proj", "model.language_model.layers.6.self_attn.q_proj", "model.language_model.layers.6.self_attn.k_proj", "model.language_model.layers.6.self_attn.v_proj", "model.language_model.layers.6.self_attn.o_proj", "model.language_model.layers.6.mlp.gate_proj", "model.language_model.layers.6.mlp.up_proj", "model.language_model.layers.6.mlp.down_proj", "model.language_model.layers.7.self_attn.q_proj", "model.language_model.layers.7.self_attn.k_proj", "model.language_model.layers.7.self_attn.v_proj", "model.language_model.layers.7.self_attn.o_proj", "model.language_model.layers.7.mlp.gate_proj", "model.language_model.layers.7.mlp.up_proj", "model.language_model.layers.7.mlp.down_proj", "model.language_model.layers.8.self_attn.q_proj", "model.language_model.layers.8.self_attn.k_proj", "model.language_model.layers.8.self_attn.v_proj", "model.language_model.layers.8.self_attn.o_proj", "model.language_model.layers.8.mlp.gate_proj", "model.language_model.layers.8.mlp.up_proj", "model.language_model.layers.8.mlp.down_proj", "model.language_model.layers.9.self_attn.q_proj", "model.language_model.layers.9.self_attn.k_proj", "model.language_model.layers.9.self_attn.v_proj", "model.language_model.layers.9.self_attn.o_proj", "model.language_model.layers.9.mlp.gate_proj", "model.language_model.layers.9.mlp.up_proj", "model.language_model.layers.9.mlp.down_proj", "model.language_model.layers.10.self_attn.q_proj", "model.language_model.layers.10.self_attn.k_proj", "model.language_model.layers.10.self_attn.v_proj", "model.language_model.layers.10.self_attn.o_proj", "model.language_model.layers.10.mlp.gate_proj", "model.language_model.layers.10.mlp.up_proj", "model.language_model.layers.10.mlp.down_proj", "model.language_model.layers.11.self_attn.q_proj", "model.language_model.layers.11.self_attn.k_proj", "model.language_model.layers.11.self_attn.v_proj", "model.language_model.layers.11.self_attn.o_proj", "model.language_model.layers.11.mlp.gate_proj", "model.language_model.layers.11.mlp.up_proj", "model.language_model.layers.11.mlp.down_proj", "model.language_model.layers.12.self_attn.q_proj", "model.language_model.layers.12.self_attn.k_proj", "model.language_model.layers.12.self_attn.v_proj", "model.language_model.layers.12.self_attn.o_proj", "model.language_model.layers.12.mlp.gate_proj", "model.language_model.layers.12.mlp.up_proj", "model.language_model.layers.12.mlp.down_proj", "model.language_model.layers.13.self_attn.q_proj", "model.language_model.layers.13.self_attn.k_proj", "model.language_model.layers.13.self_attn.v_proj", "model.language_model.layers.13.self_attn.o_proj", "model.language_model.layers.13.mlp.gate_proj", "model.language_model.layers.13.mlp.up_proj", "model.language_model.layers.13.mlp.down_proj", "model.language_model.layers.14.self_attn.q_proj", "model.language_model.layers.14.self_attn.k_proj", "model.language_model.layers.14.self_attn.v_proj", "model.language_model.layers.14.self_attn.o_proj", "model.language_model.layers.14.mlp.gate_proj", "model.language_model.layers.14.mlp.up_proj", "model.language_model.layers.14.mlp.down_proj", "model.language_model.layers.15.self_attn.q_proj", "model.language_model.layers.15.self_attn.k_proj", "model.language_model.layers.15.self_attn.v_proj", "model.language_model.layers.15.self_attn.o_proj", "model.language_model.layers.15.mlp.gate_proj", "model.language_model.layers.15.mlp.up_proj", "model.language_model.layers.15.mlp.down_proj", "model.language_model.layers.16.self_attn.q_proj", "model.language_model.layers.16.self_attn.k_proj", "model.language_model.layers.16.self_attn.v_proj", "model.language_model.layers.16.self_attn.o_proj", "model.language_model.layers.16.mlp.gate_proj", "model.language_model.layers.16.mlp.up_proj", "model.language_model.layers.16.mlp.down_proj", "model.language_model.layers.17.self_attn.q_proj", "model.language_model.layers.17.self_attn.k_proj", "model.language_model.layers.17.self_attn.v_proj", "model.language_model.layers.17.self_attn.o_proj", "model.language_model.layers.17.mlp.gate_proj", "model.language_model.layers.17.mlp.up_proj", "model.language_model.layers.17.mlp.down_proj", "model.language_model.layers.18.self_attn.q_proj", "model.language_model.layers.18.self_attn.k_proj", "model.language_model.layers.18.self_attn.v_proj", "model.language_model.layers.18.self_attn.o_proj", "model.language_model.layers.18.mlp.gate_proj", "model.language_model.layers.18.mlp.up_proj", "model.language_model.layers.18.mlp.down_proj", "model.language_model.layers.19.self_attn.q_proj", "model.language_model.layers.19.self_attn.k_proj", "model.language_model.layers.19.self_attn.v_proj", "model.language_model.layers.19.self_attn.o_proj", "model.language_model.layers.19.mlp.gate_proj", "model.language_model.layers.19.mlp.up_proj", "model.language_model.layers.19.mlp.down_proj", "model.language_model.layers.20.self_attn.q_proj", "model.language_model.layers.20.self_attn.k_proj", "model.language_model.layers.20.self_attn.v_proj", "model.language_model.layers.20.self_attn.o_proj", "model.language_model.layers.20.mlp.gate_proj", "model.language_model.layers.20.mlp.up_proj", "model.language_model.layers.20.mlp.down_proj", "model.language_model.layers.21.self_attn.q_proj", "model.language_model.layers.21.self_attn.k_proj", "model.language_model.layers.21.self_attn.v_proj", "model.language_model.layers.21.self_attn.o_proj", "model.language_model.layers.21.mlp.gate_proj", "model.language_model.layers.21.mlp.up_proj", "model.language_model.layers.21.mlp.down_proj", "model.language_model.layers.22.self_attn.q_proj", "model.language_model.layers.22.self_attn.k_proj", "model.language_model.layers.22.self_attn.v_proj", "model.language_model.layers.22.self_attn.o_proj", "model.language_model.layers.22.mlp.gate_proj", "model.language_model.layers.22.mlp.up_proj", "model.language_model.layers.22.mlp.down_proj", "model.language_model.layers.23.self_attn.q_proj", "model.language_model.layers.23.self_attn.k_proj", "model.language_model.layers.23.self_attn.v_proj", "model.language_model.layers.23.self_attn.o_proj", "model.language_model.layers.23.mlp.gate_proj", "model.language_model.layers.23.mlp.up_proj", "model.language_model.layers.23.mlp.down_proj", "model.language_model.layers.24.self_attn.q_proj", "model.language_model.layers.24.self_attn.k_proj", "model.language_model.layers.24.self_attn.v_proj", "model.language_model.layers.24.self_attn.o_proj", "model.language_model.layers.24.mlp.gate_proj", "model.language_model.layers.24.mlp.up_proj", "model.language_model.layers.24.mlp.down_proj", "model.language_model.layers.25.self_attn.q_proj", "model.language_model.layers.25.self_attn.k_proj", "model.language_model.layers.25.self_attn.v_proj", "model.language_model.layers.25.self_attn.o_proj", "model.language_model.layers.25.mlp.gate_proj", "model.language_model.layers.25.mlp.up_proj", "model.language_model.layers.25.mlp.down_proj", "model.language_model.layers.26.self_attn.q_proj", "model.language_model.layers.26.self_attn.k_proj", "model.language_model.layers.26.self_attn.v_proj", "model.language_model.layers.26.self_attn.o_proj", "model.language_model.layers.26.mlp.gate_proj", "model.language_model.layers.26.mlp.up_proj", "model.language_model.layers.26.mlp.down_proj", "model.language_model.layers.27.self_attn.q_proj", "model.language_model.layers.27.self_attn.k_proj", "model.language_model.layers.27.self_attn.v_proj", "model.language_model.layers.27.self_attn.o_proj", "model.language_model.layers.27.mlp.gate_proj", "model.language_model.layers.27.mlp.up_proj", "model.language_model.layers.27.mlp.down_proj", "model.language_model.layers.28.self_attn.q_proj", "model.language_model.layers.28.self_attn.k_proj", "model.language_model.layers.28.self_attn.v_proj", "model.language_model.layers.28.self_attn.o_proj", "model.language_model.layers.28.mlp.gate_proj", "model.language_model.layers.28.mlp.up_proj", "model.language_model.layers.28.mlp.down_proj", "model.language_model.layers.29.self_attn.q_proj", "model.language_model.layers.29.self_attn.k_proj", "model.language_model.layers.29.self_attn.v_proj", "model.language_model.layers.29.self_attn.o_proj", "model.language_model.layers.29.mlp.gate_proj", "model.language_model.layers.29.mlp.up_proj", "model.language_model.layers.29.mlp.down_proj", "model.language_model.layers.30.self_attn.q_proj", "model.language_model.layers.30.self_attn.k_proj", "model.language_model.layers.30.self_attn.v_proj", "model.language_model.layers.30.self_attn.o_proj", "model.language_model.layers.30.mlp.gate_proj", "model.language_model.layers.30.mlp.up_proj", "model.language_model.layers.30.mlp.down_proj", "model.language_model.layers.31.self_attn.q_proj", "model.language_model.layers.31.self_attn.k_proj", "model.language_model.layers.31.self_attn.v_proj", "model.language_model.layers.31.self_attn.o_proj", "model.language_model.layers.31.mlp.gate_proj", "model.language_model.layers.31.mlp.up_proj", "model.language_model.layers.31.mlp.down_proj", "model.language_model.layers.32.self_attn.q_proj", "model.language_model.layers.32.self_attn.k_proj", "model.language_model.layers.32.self_attn.v_proj", "model.language_model.layers.32.self_attn.o_proj", "model.language_model.layers.32.mlp.gate_proj", "model.language_model.layers.32.mlp.up_proj", "model.language_model.layers.32.mlp.down_proj", "model.language_model.layers.33.self_attn.q_proj", "model.language_model.layers.33.self_attn.k_proj", "model.language_model.layers.33.self_attn.v_proj", "model.language_model.layers.33.self_attn.o_proj", "model.language_model.layers.33.mlp.gate_proj", "model.language_model.layers.33.mlp.up_proj", "model.language_model.layers.33.mlp.down_proj", "model.language_model.layers.34.self_attn.q_proj", "model.language_model.layers.34.self_attn.k_proj", "model.language_model.layers.34.self_attn.v_proj", "model.language_model.layers.34.self_attn.o_proj", "model.language_model.layers.34.mlp.gate_proj", "model.language_model.layers.34.mlp.up_proj", "model.language_model.layers.34.mlp.down_proj", "model.language_model.layers.35.self_attn.q_proj", "model.language_model.layers.35.self_attn.k_proj", "model.language_model.layers.35.self_attn.v_proj", "model.language_model.layers.35.self_attn.o_proj", "model.language_model.layers.35.mlp.gate_proj", "model.language_model.layers.35.mlp.up_proj", "model.language_model.layers.35.mlp.down_proj" ], "parameter_dtypes": { "torch.bfloat16": 1821356272, "torch.int8": 6945767424 }, "int8_parameters": 6945767424, "source_files": [ { "path": "text_encoder/config.json", "size": 1542, "sha256": "89050cba6b66c4f68f52305b54fc37efe28d95232246b94aa8dc0cfa36f3b734" }, { "path": "text_encoder/generation_config.json", "size": 241, "sha256": "d04d0c6fdd1dc056cf68178425a3ecf17a0b9e848cf1a8378ad31c623263472c" }, { "path": "text_encoder/model.safetensors", "size": 17534340584, "sha256": "a1eee8233f3063466dd3b06e857b0a2cf13a77c543908374771d51a546beb2e0" } ] }