| { |
| "architectures": [ |
| "KimiK25ForConditionalGeneration" |
| ], |
| "auto_map": { |
| "AutoConfig": "configuration_kimi_k25.KimiK25Config", |
| "AutoModel": "modeling_kimi_k25.KimiK25ForConditionalGeneration", |
| "AutoModelForCausalLM": "modeling_kimi_k25.KimiK25ForConditionalGeneration" |
| }, |
| "bos_token_id": 163584, |
| "dtype": "bfloat16", |
| "eos_token_id": 163586, |
| "ignore_index": -100, |
| "media_placeholder_token_id": 163605, |
| "model_type": "kimi_k25", |
| "pad_token_id": 163839, |
| "quantization_config": { |
| "config_groups": { |
| "group_0": { |
| "format": "nvfp4-pack-quantized", |
| "input_activations": { |
| "actorder": null, |
| "block_structure": null, |
| "dynamic": "local", |
| "group_size": 16, |
| "num_bits": 4, |
| "observer": "static_minmax", |
| "observer_kwargs": {}, |
| "scale_dtype": "torch.float8_e4m3fn", |
| "strategy": "tensor_group", |
| "symmetric": true, |
| "type": "float", |
| "zp_dtype": null |
| }, |
| "output_activations": null, |
| "targets": [ |
| "Linear" |
| ], |
| "weights": { |
| "actorder": null, |
| "block_structure": null, |
| "dynamic": false, |
| "group_size": 16, |
| "num_bits": 4, |
| "observer": "memoryless_minmax", |
| "observer_kwargs": {}, |
| "scale_dtype": "torch.float8_e4m3fn", |
| "strategy": "tensor_group", |
| "symmetric": true, |
| "type": "float", |
| "zp_dtype": null |
| } |
| } |
| }, |
| "format": "nvfp4-pack-quantized", |
| "global_compression_ratio": null, |
| "ignore": [ |
| "vision_tower.encoder.blocks.0.mlp.fc0", |
| "vision_tower.encoder.blocks.0.mlp.fc1", |
| "vision_tower.encoder.blocks.0.wqkv", |
| "vision_tower.encoder.blocks.0.wo", |
| "vision_tower.encoder.blocks.1.mlp.fc0", |
| "vision_tower.encoder.blocks.1.mlp.fc1", |
| "vision_tower.encoder.blocks.1.wqkv", |
| "vision_tower.encoder.blocks.1.wo", |
| "vision_tower.encoder.blocks.2.mlp.fc0", |
| "vision_tower.encoder.blocks.2.mlp.fc1", |
| "vision_tower.encoder.blocks.2.wqkv", |
| "vision_tower.encoder.blocks.2.wo", |
| "vision_tower.encoder.blocks.3.mlp.fc0", |
| "vision_tower.encoder.blocks.3.mlp.fc1", |
| "vision_tower.encoder.blocks.3.wqkv", |
| "vision_tower.encoder.blocks.3.wo", |
| "vision_tower.encoder.blocks.4.mlp.fc0", |
| "vision_tower.encoder.blocks.4.mlp.fc1", |
| "vision_tower.encoder.blocks.4.wqkv", |
| "vision_tower.encoder.blocks.4.wo", |
| "vision_tower.encoder.blocks.5.mlp.fc0", |
| "vision_tower.encoder.blocks.5.mlp.fc1", |
| "vision_tower.encoder.blocks.5.wqkv", |
| "vision_tower.encoder.blocks.5.wo", |
| "vision_tower.encoder.blocks.6.mlp.fc0", |
| "vision_tower.encoder.blocks.6.mlp.fc1", |
| "vision_tower.encoder.blocks.6.wqkv", |
| "vision_tower.encoder.blocks.6.wo", |
| "vision_tower.encoder.blocks.7.mlp.fc0", |
| "vision_tower.encoder.blocks.7.mlp.fc1", |
| "vision_tower.encoder.blocks.7.wqkv", |
| "vision_tower.encoder.blocks.7.wo", |
| "vision_tower.encoder.blocks.8.mlp.fc0", |
| "vision_tower.encoder.blocks.8.mlp.fc1", |
| "vision_tower.encoder.blocks.8.wqkv", |
| "vision_tower.encoder.blocks.8.wo", |
| "vision_tower.encoder.blocks.9.mlp.fc0", |
| "vision_tower.encoder.blocks.9.mlp.fc1", |
| "vision_tower.encoder.blocks.9.wqkv", |
| "vision_tower.encoder.blocks.9.wo", |
| "vision_tower.encoder.blocks.10.mlp.fc0", |
| "vision_tower.encoder.blocks.10.mlp.fc1", |
| "vision_tower.encoder.blocks.10.wqkv", |
| "vision_tower.encoder.blocks.10.wo", |
| "vision_tower.encoder.blocks.11.mlp.fc0", |
| "vision_tower.encoder.blocks.11.mlp.fc1", |
| "vision_tower.encoder.blocks.11.wqkv", |
| "vision_tower.encoder.blocks.11.wo", |
| "vision_tower.encoder.blocks.12.mlp.fc0", |
| "vision_tower.encoder.blocks.12.mlp.fc1", |
| "vision_tower.encoder.blocks.12.wqkv", |
| "vision_tower.encoder.blocks.12.wo", |
| "vision_tower.encoder.blocks.13.mlp.fc0", |
| "vision_tower.encoder.blocks.13.mlp.fc1", |
| "vision_tower.encoder.blocks.13.wqkv", |
| "vision_tower.encoder.blocks.13.wo", |
| "vision_tower.encoder.blocks.14.mlp.fc0", |
| "vision_tower.encoder.blocks.14.mlp.fc1", |
| "vision_tower.encoder.blocks.14.wqkv", |
| "vision_tower.encoder.blocks.14.wo", |
| "vision_tower.encoder.blocks.15.mlp.fc0", |
| "vision_tower.encoder.blocks.15.mlp.fc1", |
| "vision_tower.encoder.blocks.15.wqkv", |
| "vision_tower.encoder.blocks.15.wo", |
| "vision_tower.encoder.blocks.16.mlp.fc0", |
| "vision_tower.encoder.blocks.16.mlp.fc1", |
| "vision_tower.encoder.blocks.16.wqkv", |
| "vision_tower.encoder.blocks.16.wo", |
| "vision_tower.encoder.blocks.17.mlp.fc0", |
| "vision_tower.encoder.blocks.17.mlp.fc1", |
| "vision_tower.encoder.blocks.17.wqkv", |
| "vision_tower.encoder.blocks.17.wo", |
| "vision_tower.encoder.blocks.18.mlp.fc0", |
| "vision_tower.encoder.blocks.18.mlp.fc1", |
| "vision_tower.encoder.blocks.18.wqkv", |
| "vision_tower.encoder.blocks.18.wo", |
| "vision_tower.encoder.blocks.19.mlp.fc0", |
| "vision_tower.encoder.blocks.19.mlp.fc1", |
| "vision_tower.encoder.blocks.19.wqkv", |
| "vision_tower.encoder.blocks.19.wo", |
| "vision_tower.encoder.blocks.20.mlp.fc0", |
| "vision_tower.encoder.blocks.20.mlp.fc1", |
| "vision_tower.encoder.blocks.20.wqkv", |
| "vision_tower.encoder.blocks.20.wo", |
| "vision_tower.encoder.blocks.21.mlp.fc0", |
| "vision_tower.encoder.blocks.21.mlp.fc1", |
| "vision_tower.encoder.blocks.21.wqkv", |
| "vision_tower.encoder.blocks.21.wo", |
| "vision_tower.encoder.blocks.22.mlp.fc0", |
| "vision_tower.encoder.blocks.22.mlp.fc1", |
| "vision_tower.encoder.blocks.22.wqkv", |
| "vision_tower.encoder.blocks.22.wo", |
| "vision_tower.encoder.blocks.23.mlp.fc0", |
| "vision_tower.encoder.blocks.23.mlp.fc1", |
| "vision_tower.encoder.blocks.23.wqkv", |
| "vision_tower.encoder.blocks.23.wo", |
| "vision_tower.encoder.blocks.24.mlp.fc0", |
| "vision_tower.encoder.blocks.24.mlp.fc1", |
| "vision_tower.encoder.blocks.24.wqkv", |
| "vision_tower.encoder.blocks.24.wo", |
| "vision_tower.encoder.blocks.25.mlp.fc0", |
| "vision_tower.encoder.blocks.25.mlp.fc1", |
| "vision_tower.encoder.blocks.25.wqkv", |
| "vision_tower.encoder.blocks.25.wo", |
| "vision_tower.encoder.blocks.26.mlp.fc0", |
| "vision_tower.encoder.blocks.26.mlp.fc1", |
| "vision_tower.encoder.blocks.26.wqkv", |
| "vision_tower.encoder.blocks.26.wo", |
| "mm_projector.proj.0", |
| "mm_projector.proj.2", |
| "language_model.model.layers.0.self_attn.q_a_proj", |
| "language_model.model.layers.0.self_attn.q_b_proj", |
| "language_model.model.layers.0.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.0.self_attn.kv_b_proj", |
| "language_model.model.layers.0.self_attn.o_proj", |
| "language_model.model.layers.1.self_attn.q_a_proj", |
| "language_model.model.layers.1.self_attn.q_b_proj", |
| "language_model.model.layers.1.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.1.self_attn.kv_b_proj", |
| "language_model.model.layers.1.self_attn.o_proj", |
| "language_model.model.layers.2.self_attn.q_a_proj", |
| "language_model.model.layers.2.self_attn.q_b_proj", |
| "language_model.model.layers.2.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.2.self_attn.kv_b_proj", |
| "language_model.model.layers.2.self_attn.o_proj", |
| "language_model.model.layers.3.self_attn.q_a_proj", |
| "language_model.model.layers.3.self_attn.q_b_proj", |
| "language_model.model.layers.3.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.3.self_attn.kv_b_proj", |
| "language_model.model.layers.3.self_attn.o_proj", |
| "language_model.model.layers.4.self_attn.q_a_proj", |
| "language_model.model.layers.4.self_attn.q_b_proj", |
| "language_model.model.layers.4.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.4.self_attn.kv_b_proj", |
| "language_model.model.layers.4.self_attn.o_proj", |
| "language_model.model.layers.5.self_attn.q_a_proj", |
| "language_model.model.layers.5.self_attn.q_b_proj", |
| "language_model.model.layers.5.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.5.self_attn.kv_b_proj", |
| "language_model.model.layers.5.self_attn.o_proj", |
| "language_model.model.layers.6.self_attn.q_a_proj", |
| "language_model.model.layers.6.self_attn.q_b_proj", |
| "language_model.model.layers.6.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.6.self_attn.kv_b_proj", |
| "language_model.model.layers.6.self_attn.o_proj", |
| "language_model.model.layers.7.self_attn.q_a_proj", |
| "language_model.model.layers.7.self_attn.q_b_proj", |
| "language_model.model.layers.7.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.7.self_attn.kv_b_proj", |
| "language_model.model.layers.7.self_attn.o_proj", |
| "language_model.model.layers.8.self_attn.q_a_proj", |
| "language_model.model.layers.8.self_attn.q_b_proj", |
| "language_model.model.layers.8.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.8.self_attn.kv_b_proj", |
| "language_model.model.layers.8.self_attn.o_proj", |
| "language_model.model.layers.9.self_attn.q_a_proj", |
| "language_model.model.layers.9.self_attn.q_b_proj", |
| "language_model.model.layers.9.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.9.self_attn.kv_b_proj", |
| "language_model.model.layers.9.self_attn.o_proj", |
| "language_model.model.layers.10.self_attn.q_a_proj", |
| "language_model.model.layers.10.self_attn.q_b_proj", |
| "language_model.model.layers.10.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.10.self_attn.kv_b_proj", |
| "language_model.model.layers.10.self_attn.o_proj", |
| "language_model.model.layers.11.self_attn.q_a_proj", |
| "language_model.model.layers.11.self_attn.q_b_proj", |
| "language_model.model.layers.11.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.11.self_attn.kv_b_proj", |
| "language_model.model.layers.11.self_attn.o_proj", |
| "language_model.model.layers.12.self_attn.q_a_proj", |
| "language_model.model.layers.12.self_attn.q_b_proj", |
| "language_model.model.layers.12.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.12.self_attn.kv_b_proj", |
| "language_model.model.layers.12.self_attn.o_proj", |
| "language_model.model.layers.13.self_attn.q_a_proj", |
| "language_model.model.layers.13.self_attn.q_b_proj", |
| "language_model.model.layers.13.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.13.self_attn.kv_b_proj", |
| "language_model.model.layers.13.self_attn.o_proj", |
| "language_model.model.layers.14.self_attn.q_a_proj", |
| "language_model.model.layers.14.self_attn.q_b_proj", |
| "language_model.model.layers.14.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.14.self_attn.kv_b_proj", |
| "language_model.model.layers.14.self_attn.o_proj", |
| "language_model.model.layers.15.self_attn.q_a_proj", |
| "language_model.model.layers.15.self_attn.q_b_proj", |
| "language_model.model.layers.15.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.15.self_attn.kv_b_proj", |
| "language_model.model.layers.15.self_attn.o_proj", |
| "language_model.model.layers.16.self_attn.q_a_proj", |
| "language_model.model.layers.16.self_attn.q_b_proj", |
| "language_model.model.layers.16.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.16.self_attn.kv_b_proj", |
| "language_model.model.layers.16.self_attn.o_proj", |
| "language_model.model.layers.17.self_attn.q_a_proj", |
| "language_model.model.layers.17.self_attn.q_b_proj", |
| "language_model.model.layers.17.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.17.self_attn.kv_b_proj", |
| "language_model.model.layers.17.self_attn.o_proj", |
| "language_model.model.layers.18.self_attn.q_a_proj", |
| "language_model.model.layers.18.self_attn.q_b_proj", |
| "language_model.model.layers.18.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.18.self_attn.kv_b_proj", |
| "language_model.model.layers.18.self_attn.o_proj", |
| "language_model.model.layers.19.self_attn.q_a_proj", |
| "language_model.model.layers.19.self_attn.q_b_proj", |
| "language_model.model.layers.19.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.19.self_attn.kv_b_proj", |
| "language_model.model.layers.19.self_attn.o_proj", |
| "language_model.model.layers.20.self_attn.q_a_proj", |
| "language_model.model.layers.20.self_attn.q_b_proj", |
| "language_model.model.layers.20.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.20.self_attn.kv_b_proj", |
| "language_model.model.layers.20.self_attn.o_proj", |
| "language_model.model.layers.21.self_attn.q_a_proj", |
| "language_model.model.layers.21.self_attn.q_b_proj", |
| "language_model.model.layers.21.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.21.self_attn.kv_b_proj", |
| "language_model.model.layers.21.self_attn.o_proj", |
| "language_model.model.layers.22.self_attn.q_a_proj", |
| "language_model.model.layers.22.self_attn.q_b_proj", |
| "language_model.model.layers.22.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.22.self_attn.kv_b_proj", |
| "language_model.model.layers.22.self_attn.o_proj", |
| "language_model.model.layers.23.self_attn.q_a_proj", |
| "language_model.model.layers.23.self_attn.q_b_proj", |
| "language_model.model.layers.23.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.23.self_attn.kv_b_proj", |
| "language_model.model.layers.23.self_attn.o_proj", |
| "language_model.model.layers.24.self_attn.q_a_proj", |
| "language_model.model.layers.24.self_attn.q_b_proj", |
| "language_model.model.layers.24.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.24.self_attn.kv_b_proj", |
| "language_model.model.layers.24.self_attn.o_proj", |
| "language_model.model.layers.25.self_attn.q_a_proj", |
| "language_model.model.layers.25.self_attn.q_b_proj", |
| "language_model.model.layers.25.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.25.self_attn.kv_b_proj", |
| "language_model.model.layers.25.self_attn.o_proj", |
| "language_model.model.layers.26.self_attn.q_a_proj", |
| "language_model.model.layers.26.self_attn.q_b_proj", |
| "language_model.model.layers.26.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.26.self_attn.kv_b_proj", |
| "language_model.model.layers.26.self_attn.o_proj", |
| "language_model.model.layers.27.self_attn.q_a_proj", |
| "language_model.model.layers.27.self_attn.q_b_proj", |
| "language_model.model.layers.27.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.27.self_attn.kv_b_proj", |
| "language_model.model.layers.27.self_attn.o_proj", |
| "language_model.model.layers.28.self_attn.q_a_proj", |
| "language_model.model.layers.28.self_attn.q_b_proj", |
| "language_model.model.layers.28.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.28.self_attn.kv_b_proj", |
| "language_model.model.layers.28.self_attn.o_proj", |
| "language_model.model.layers.29.self_attn.q_a_proj", |
| "language_model.model.layers.29.self_attn.q_b_proj", |
| "language_model.model.layers.29.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.29.self_attn.kv_b_proj", |
| "language_model.model.layers.29.self_attn.o_proj", |
| "language_model.model.layers.30.self_attn.q_a_proj", |
| "language_model.model.layers.30.self_attn.q_b_proj", |
| "language_model.model.layers.30.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.30.self_attn.kv_b_proj", |
| "language_model.model.layers.30.self_attn.o_proj", |
| "language_model.model.layers.31.self_attn.q_a_proj", |
| "language_model.model.layers.31.self_attn.q_b_proj", |
| "language_model.model.layers.31.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.31.self_attn.kv_b_proj", |
| "language_model.model.layers.31.self_attn.o_proj", |
| "language_model.model.layers.32.self_attn.q_a_proj", |
| "language_model.model.layers.32.self_attn.q_b_proj", |
| "language_model.model.layers.32.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.32.self_attn.kv_b_proj", |
| "language_model.model.layers.32.self_attn.o_proj", |
| "language_model.model.layers.33.self_attn.q_a_proj", |
| "language_model.model.layers.33.self_attn.q_b_proj", |
| "language_model.model.layers.33.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.33.self_attn.kv_b_proj", |
| "language_model.model.layers.33.self_attn.o_proj", |
| "language_model.model.layers.34.self_attn.q_a_proj", |
| "language_model.model.layers.34.self_attn.q_b_proj", |
| "language_model.model.layers.34.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.34.self_attn.kv_b_proj", |
| "language_model.model.layers.34.self_attn.o_proj", |
| "language_model.model.layers.35.self_attn.q_a_proj", |
| "language_model.model.layers.35.self_attn.q_b_proj", |
| "language_model.model.layers.35.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.35.self_attn.kv_b_proj", |
| "language_model.model.layers.35.self_attn.o_proj", |
| "language_model.model.layers.36.self_attn.q_a_proj", |
| "language_model.model.layers.36.self_attn.q_b_proj", |
| "language_model.model.layers.36.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.36.self_attn.kv_b_proj", |
| "language_model.model.layers.36.self_attn.o_proj", |
| "language_model.model.layers.37.self_attn.q_a_proj", |
| "language_model.model.layers.37.self_attn.q_b_proj", |
| "language_model.model.layers.37.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.37.self_attn.kv_b_proj", |
| "language_model.model.layers.37.self_attn.o_proj", |
| "language_model.model.layers.38.self_attn.q_a_proj", |
| "language_model.model.layers.38.self_attn.q_b_proj", |
| "language_model.model.layers.38.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.38.self_attn.kv_b_proj", |
| "language_model.model.layers.38.self_attn.o_proj", |
| "language_model.model.layers.39.self_attn.q_a_proj", |
| "language_model.model.layers.39.self_attn.q_b_proj", |
| "language_model.model.layers.39.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.39.self_attn.kv_b_proj", |
| "language_model.model.layers.39.self_attn.o_proj", |
| "language_model.model.layers.40.self_attn.q_a_proj", |
| "language_model.model.layers.40.self_attn.q_b_proj", |
| "language_model.model.layers.40.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.40.self_attn.kv_b_proj", |
| "language_model.model.layers.40.self_attn.o_proj", |
| "language_model.model.layers.41.self_attn.q_a_proj", |
| "language_model.model.layers.41.self_attn.q_b_proj", |
| "language_model.model.layers.41.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.41.self_attn.kv_b_proj", |
| "language_model.model.layers.41.self_attn.o_proj", |
| "language_model.model.layers.42.self_attn.q_a_proj", |
| "language_model.model.layers.42.self_attn.q_b_proj", |
| "language_model.model.layers.42.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.42.self_attn.kv_b_proj", |
| "language_model.model.layers.42.self_attn.o_proj", |
| "language_model.model.layers.43.self_attn.q_a_proj", |
| "language_model.model.layers.43.self_attn.q_b_proj", |
| "language_model.model.layers.43.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.43.self_attn.kv_b_proj", |
| "language_model.model.layers.43.self_attn.o_proj", |
| "language_model.model.layers.44.self_attn.q_a_proj", |
| "language_model.model.layers.44.self_attn.q_b_proj", |
| "language_model.model.layers.44.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.44.self_attn.kv_b_proj", |
| "language_model.model.layers.44.self_attn.o_proj", |
| "language_model.model.layers.45.self_attn.q_a_proj", |
| "language_model.model.layers.45.self_attn.q_b_proj", |
| "language_model.model.layers.45.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.45.self_attn.kv_b_proj", |
| "language_model.model.layers.45.self_attn.o_proj", |
| "language_model.model.layers.46.self_attn.q_a_proj", |
| "language_model.model.layers.46.self_attn.q_b_proj", |
| "language_model.model.layers.46.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.46.self_attn.kv_b_proj", |
| "language_model.model.layers.46.self_attn.o_proj", |
| "language_model.model.layers.47.self_attn.q_a_proj", |
| "language_model.model.layers.47.self_attn.q_b_proj", |
| "language_model.model.layers.47.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.47.self_attn.kv_b_proj", |
| "language_model.model.layers.47.self_attn.o_proj", |
| "language_model.model.layers.48.self_attn.q_a_proj", |
| "language_model.model.layers.48.self_attn.q_b_proj", |
| "language_model.model.layers.48.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.48.self_attn.kv_b_proj", |
| "language_model.model.layers.48.self_attn.o_proj", |
| "language_model.model.layers.49.self_attn.q_a_proj", |
| "language_model.model.layers.49.self_attn.q_b_proj", |
| "language_model.model.layers.49.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.49.self_attn.kv_b_proj", |
| "language_model.model.layers.49.self_attn.o_proj", |
| "language_model.model.layers.50.self_attn.q_a_proj", |
| "language_model.model.layers.50.self_attn.q_b_proj", |
| "language_model.model.layers.50.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.50.self_attn.kv_b_proj", |
| "language_model.model.layers.50.self_attn.o_proj", |
| "language_model.model.layers.51.self_attn.q_a_proj", |
| "language_model.model.layers.51.self_attn.q_b_proj", |
| "language_model.model.layers.51.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.51.self_attn.kv_b_proj", |
| "language_model.model.layers.51.self_attn.o_proj", |
| "language_model.model.layers.52.self_attn.q_a_proj", |
| "language_model.model.layers.52.self_attn.q_b_proj", |
| "language_model.model.layers.52.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.52.self_attn.kv_b_proj", |
| "language_model.model.layers.52.self_attn.o_proj", |
| "language_model.model.layers.53.self_attn.q_a_proj", |
| "language_model.model.layers.53.self_attn.q_b_proj", |
| "language_model.model.layers.53.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.53.self_attn.kv_b_proj", |
| "language_model.model.layers.53.self_attn.o_proj", |
| "language_model.model.layers.54.self_attn.q_a_proj", |
| "language_model.model.layers.54.self_attn.q_b_proj", |
| "language_model.model.layers.54.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.54.self_attn.kv_b_proj", |
| "language_model.model.layers.54.self_attn.o_proj", |
| "language_model.model.layers.55.self_attn.q_a_proj", |
| "language_model.model.layers.55.self_attn.q_b_proj", |
| "language_model.model.layers.55.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.55.self_attn.kv_b_proj", |
| "language_model.model.layers.55.self_attn.o_proj", |
| "language_model.model.layers.56.self_attn.q_a_proj", |
| "language_model.model.layers.56.self_attn.q_b_proj", |
| "language_model.model.layers.56.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.56.self_attn.kv_b_proj", |
| "language_model.model.layers.56.self_attn.o_proj", |
| "language_model.model.layers.57.self_attn.q_a_proj", |
| "language_model.model.layers.57.self_attn.q_b_proj", |
| "language_model.model.layers.57.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.57.self_attn.kv_b_proj", |
| "language_model.model.layers.57.self_attn.o_proj", |
| "language_model.model.layers.58.self_attn.q_a_proj", |
| "language_model.model.layers.58.self_attn.q_b_proj", |
| "language_model.model.layers.58.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.58.self_attn.kv_b_proj", |
| "language_model.model.layers.58.self_attn.o_proj", |
| "language_model.model.layers.59.self_attn.q_a_proj", |
| "language_model.model.layers.59.self_attn.q_b_proj", |
| "language_model.model.layers.59.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.59.self_attn.kv_b_proj", |
| "language_model.model.layers.59.self_attn.o_proj", |
| "language_model.model.layers.60.self_attn.q_a_proj", |
| "language_model.model.layers.60.self_attn.q_b_proj", |
| "language_model.model.layers.60.self_attn.kv_a_proj_with_mqa", |
| "language_model.model.layers.60.self_attn.kv_b_proj", |
| "language_model.model.layers.60.self_attn.o_proj", |
| "language_model.lm_head" |
| ], |
| "kv_cache_scheme": null, |
| "quant_method": "compressed-tensors", |
| "quantization_status": "compressed", |
| "sparsity_config": {}, |
| "transform_config": {}, |
| "version": "0.15.1.dev17+gfa3fa2d" |
| }, |
| "text_config": { |
| "_name_or_path": "", |
| "add_cross_attention": false, |
| "architectures": [ |
| "DeepseekV3ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "configuration_deepseek.DeepseekV3Config", |
| "AutoModel": "modeling_deepseek.DeepseekV3Model", |
| "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM" |
| }, |
| "aux_loss_alpha": 0.001, |
| "bad_words_ids": null, |
| "begin_suppress_tokens": null, |
| "bos_token_id": 163584, |
| "chunk_size_feed_forward": 0, |
| "cross_attention_hidden_size": null, |
| "decoder_start_token_id": null, |
| "diversity_penalty": 0.0, |
| "do_sample": false, |
| "dtype": "bfloat16", |
| "early_stopping": false, |
| "encoder_no_repeat_ngram_size": 0, |
| "eos_token_id": 163586, |
| "ep_size": 1, |
| "exponential_decay_length_penalty": null, |
| "finetuning_task": null, |
| "first_k_dense_replace": 1, |
| "forced_bos_token_id": null, |
| "forced_eos_token_id": null, |
| "hidden_act": "silu", |
| "hidden_size": 7168, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 18432, |
| "is_decoder": false, |
| "is_encoder_decoder": false, |
| "kv_lora_rank": 512, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "length_penalty": 1.0, |
| "max_length": 20, |
| "max_position_embeddings": 262144, |
| "min_length": 0, |
| "model_type": "deepseek_v3", |
| "moe_intermediate_size": 2048, |
| "moe_layer_freq": 1, |
| "n_group": 1, |
| "n_routed_experts": 384, |
| "n_shared_experts": 1, |
| "no_repeat_ngram_size": 0, |
| "norm_topk_prob": true, |
| "num_attention_heads": 64, |
| "num_beam_groups": 1, |
| "num_beams": 1, |
| "num_experts_per_tok": 8, |
| "num_hidden_layers": 61, |
| "num_key_value_heads": 64, |
| "num_nextn_predict_layers": 0, |
| "num_return_sequences": 1, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "output_scores": false, |
| "pad_token_id": 163839, |
| "prefix": null, |
| "pretraining_tp": 1, |
| "problem_type": null, |
| "pruned_heads": {}, |
| "q_lora_rank": 1536, |
| "qk_nope_head_dim": 128, |
| "qk_rope_head_dim": 64, |
| "remove_invalid_values": false, |
| "repetition_penalty": 1.0, |
| "return_dict": true, |
| "return_dict_in_generate": false, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": { |
| "beta_fast": 32.0, |
| "beta_slow": 1.0, |
| "factor": 64.0, |
| "mscale": 1.0, |
| "mscale_all_dim": 1.0, |
| "original_max_position_embeddings": 4096, |
| "type": "yarn" |
| }, |
| "rope_theta": 50000.0, |
| "routed_scaling_factor": 2.827, |
| "scoring_func": "sigmoid", |
| "sep_token_id": null, |
| "seq_aux": true, |
| "suppress_tokens": null, |
| "task_specific_params": null, |
| "temperature": 1.0, |
| "tf_legacy_loss": false, |
| "tie_encoder_decoder": false, |
| "tie_word_embeddings": false, |
| "tokenizer_class": null, |
| "top_k": 50, |
| "top_p": 1.0, |
| "topk_group": 1, |
| "topk_method": "noaux_tc", |
| "torchscript": false, |
| "typical_p": 1.0, |
| "use_bfloat16": false, |
| "use_cache": true, |
| "v_head_dim": 128, |
| "vocab_size": 163840 |
| }, |
| "tie_word_embeddings": false, |
| "transformers_version": "4.57.6", |
| "use_unified_vision_chunk": true, |
| "video_placeholder": "<|kimi_k25_video_placeholder|>", |
| "vision_config": { |
| "init_pos_emb_height": 64, |
| "init_pos_emb_time": 4, |
| "init_pos_emb_width": 64, |
| "merge_kernel_size": [ |
| 2, |
| 2 |
| ], |
| "merge_type": "sd2_tpool", |
| "mm_hidden_size": 1152, |
| "mm_projector_type": "patchmerger", |
| "model_type": "", |
| "patch_size": 14, |
| "pos_emb_type": "divided_fixed", |
| "projector_hidden_act": "gelu", |
| "projector_ln_eps": 1e-05, |
| "text_hidden_size": 7168, |
| "video_attn_type": "spatial_temporal", |
| "vt_hidden_size": 1152, |
| "vt_intermediate_size": 4304, |
| "vt_num_attention_heads": 16, |
| "vt_num_hidden_layers": 27 |
| } |
| } |
