| { | |
| "architectures": [ | |
| "YuanVLChatModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_yuanvl.YuanVLChatConfig", | |
| "AutoModel": "modeling_yuanvl_chat.YuanVLChatModel", | |
| "AutoModelForCausalLM": "modeling_yuanvl_chat.YuanVLChatModel" | |
| }, | |
| "bos_token_id": 134960, | |
| "clip_download_path": "internvit2.5-300M", | |
| "clip_model_name": "InternViT-448", | |
| "downsample_ratio": 0.5, | |
| "dynamic_image_size": true, | |
| "eos_token_id": 77185, | |
| "force_image_size": 448, | |
| "imagemlp_recompute": true, | |
| "img_context_token_id": 77188, | |
| "llm_config": { | |
| "_from_model_config": true, | |
| "architectures": [ | |
| "YuanForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "attention_projection_size": 9216, | |
| "attn_dropout": 0.0, | |
| "attn_mask_type": "causal", | |
| "auto_map": { | |
| "AutoConfig": "configuration_yuanvl.YuanConfig", | |
| "AutoModelForCausalLM": "yuanvl.YuanForCausalLM" | |
| }, | |
| "bos_token": "<BOS>", | |
| "bos_token_id": 134960, | |
| "causal_mask": true, | |
| "dropout": 0, | |
| "eod_token": "<eod>", | |
| "eod_token_id": 77185, | |
| "ffn_hidden_size": 16384, | |
| "head_dim": 256, | |
| "hidden_act": "silu", | |
| "hidden_size": 4608, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 16384, | |
| "lf_conv2d_add_bias": false, | |
| "lf_conv2d_group": 1, | |
| "lf_conv2d_num_pad": 0, | |
| "mask_token_id": 77185, | |
| "max_position_embeddings": 32768, | |
| "model_max_length": 32768, | |
| "model_type": "yuan", | |
| "moe_config": { | |
| "ffn_hidden_size": 16384, | |
| "gated_linear_unit": true, | |
| "moe_num_experts": 64, | |
| "moe_top_k": 2, | |
| "norm_topk_prob": true, | |
| "per_layer_experts_blocks": [ | |
| 40, | |
| 48, | |
| 24, | |
| 16, | |
| 24, | |
| 16, | |
| 16, | |
| 24, | |
| 32, | |
| 32, | |
| 24, | |
| 24, | |
| 24, | |
| 40, | |
| 40, | |
| 40, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 48, | |
| 40, | |
| 40, | |
| 40, | |
| 40, | |
| 40, | |
| 40, | |
| 40, | |
| 40, | |
| 32, | |
| 32, | |
| 32, | |
| 32, | |
| 32, | |
| 32, | |
| 24, | |
| 24, | |
| 16, | |
| 8 | |
| ], | |
| "router_type": "linear" | |
| }, | |
| "num_attention_heads": 36, | |
| "num_hidden_layers": 103, | |
| "num_key_value_heads": 36, | |
| "num_query_groups": 36, | |
| "output_router_logits": false, | |
| "pad_token_id": 77188, | |
| "perform_initialization": false, | |
| "reset_attention_mask": false, | |
| "reset_position_ids": false, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 1000000.0, | |
| "rotary_base": 1000000, | |
| "rotary_percent": 1.0, | |
| "sep_token": "<sep>", | |
| "sep_token_id": 77187, | |
| "tie_word_embeddings": false, | |
| "tokenizer_class": "YuanVLTokenizer", | |
| "torch_dtype": "bfloat16", | |
| "use_bias": false, | |
| "use_cache": true, | |
| "use_flash_attention": true, | |
| "use_lf_gate": true, | |
| "use_lfa_bias": false, | |
| "use_loss_mask": false, | |
| "use_moe": true, | |
| "use_rope_scaling": false, | |
| "vocab_size": 136064 | |
| }, | |
| "max_dynamic_patch": 9, | |
| "max_position_embeddings": 32768, | |
| "min_dynamic_patch": 1, | |
| "model_max_length": 32768, | |
| "model_type": "yuanvl", | |
| "output_attentions": false, | |
| "pad_token_id": 77185, | |
| "ps_version": "v2", | |
| "quantization_config": { | |
| "config_groups": { | |
| "group_0": { | |
| "format": "pack-quantized", | |
| "input_activations": null, | |
| "output_activations": null, | |
| "targets": [ | |
| "Linear" | |
| ], | |
| "weights": { | |
| "actorder": null, | |
| "block_structure": null, | |
| "dynamic": false, | |
| "group_size": 128, | |
| "num_bits": 4, | |
| "observer": "minmax", | |
| "observer_kwargs": {}, | |
| "strategy": "group", | |
| "symmetric": true, | |
| "type": "int" | |
| } | |
| } | |
| }, | |
| "format": "pack-quantized", | |
| "global_compression_ratio": null, | |
| "ignore": [ | |
| ".encoder.layers.0.attn.qkv", | |
| ".encoder.layers.0.attn.proj", | |
| ".encoder.layers.0.mlp.fc1", | |
| ".encoder.layers.0.mlp.fc2", | |
| ".encoder.layers.1.attn.qkv", | |
| ".encoder.layers.1.attn.proj", | |
| ".encoder.layers.1.mlp.fc1", | |
| ".encoder.layers.1.mlp.fc2", | |
| ".encoder.layers.2.attn.qkv", | |
| ".encoder.layers.2.attn.proj", | |
| ".encoder.layers.2.mlp.fc1", | |
| ".encoder.layers.2.mlp.fc2", | |
| ".encoder.layers.3.attn.qkv", | |
| ".encoder.layers.3.attn.proj", | |
| ".encoder.layers.3.mlp.fc1", | |
| ".encoder.layers.3.mlp.fc2", | |
| ".encoder.layers.4.attn.qkv", | |
| ".encoder.layers.4.attn.proj", | |
| ".encoder.layers.4.mlp.fc1", | |
| ".encoder.layers.4.mlp.fc2", | |
| ".encoder.layers.5.attn.qkv", | |
| ".encoder.layers.5.attn.proj", | |
| ".encoder.layers.5.mlp.fc1", | |
| ".encoder.layers.5.mlp.fc2", | |
| ".encoder.layers.6.attn.qkv", | |
| ".encoder.layers.6.attn.proj", | |
| ".encoder.layers.6.mlp.fc1", | |
| ".encoder.layers.6.mlp.fc2", | |
| ".encoder.layers.7.attn.qkv", | |
| ".encoder.layers.7.attn.proj", | |
| ".encoder.layers.7.mlp.fc1", | |
| ".encoder.layers.7.mlp.fc2", | |
| ".encoder.layers.8.attn.qkv", | |
| ".encoder.layers.8.attn.proj", | |
| ".encoder.layers.8.mlp.fc1", | |
| ".encoder.layers.8.mlp.fc2", | |
| ".encoder.layers.9.attn.qkv", | |
| ".encoder.layers.9.attn.proj", | |
| ".encoder.layers.9.mlp.fc1", | |
| ".encoder.layers.9.mlp.fc2", | |
| ".encoder.layers.10.attn.qkv", | |
| ".encoder.layers.10.attn.proj", | |
| ".encoder.layers.10.mlp.fc1", | |
| ".encoder.layers.10.mlp.fc2", | |
| ".encoder.layers.11.attn.qkv", | |
| ".encoder.layers.11.attn.proj", | |
| ".encoder.layers.11.mlp.fc1", | |
| ".encoder.layers.11.mlp.fc2", | |
| ".encoder.layers.12.attn.qkv", | |
| ".encoder.layers.12.attn.proj", | |
| ".encoder.layers.12.mlp.fc1", | |
| ".encoder.layers.12.mlp.fc2", | |
| ".encoder.layers.13.attn.qkv", | |
| ".encoder.layers.13.attn.proj", | |
| ".encoder.layers.13.mlp.fc1", | |
| ".encoder.layers.13.mlp.fc2", | |
| ".encoder.layers.14.attn.qkv", | |
| ".encoder.layers.14.attn.proj", | |
| ".encoder.layers.14.mlp.fc1", | |
| ".encoder.layers.14.mlp.fc2", | |
| ".encoder.layers.15.attn.qkv", | |
| ".encoder.layers.15.attn.proj", | |
| ".encoder.layers.15.mlp.fc1", | |
| ".encoder.layers.15.mlp.fc2", | |
| ".encoder.layers.16.attn.qkv", | |
| ".encoder.layers.16.attn.proj", | |
| ".encoder.layers.16.mlp.fc1", | |
| ".encoder.layers.16.mlp.fc2", | |
| ".encoder.layers.17.attn.qkv", | |
| ".encoder.layers.17.attn.proj", | |
| ".encoder.layers.17.mlp.fc1", | |
| ".encoder.layers.17.mlp.fc2", | |
| ".encoder.layers.18.attn.qkv", | |
| ".encoder.layers.18.attn.proj", | |
| ".encoder.layers.18.mlp.fc1", | |
| ".encoder.layers.18.mlp.fc2", | |
| ".encoder.layers.19.attn.qkv", | |
| ".encoder.layers.19.attn.proj", | |
| ".encoder.layers.19.mlp.fc1", | |
| ".encoder.layers.19.mlp.fc2", | |
| ".encoder.layers.20.attn.qkv", | |
| ".encoder.layers.20.attn.proj", | |
| ".encoder.layers.20.mlp.fc1", | |
| ".encoder.layers.20.mlp.fc2", | |
| ".encoder.layers.21.attn.qkv", | |
| ".encoder.layers.21.attn.proj", | |
| ".encoder.layers.21.mlp.fc1", | |
| ".encoder.layers.21.mlp.fc2", | |
| ".encoder.layers.22.attn.qkv", | |
| ".encoder.layers.22.attn.proj", | |
| ".encoder.layers.22.mlp.fc1", | |
| ".encoder.layers.22.mlp.fc2", | |
| ".encoder.layers.23.attn.qkv", | |
| ".encoder.layers.23.attn.proj", | |
| ".encoder.layers.23.mlp.fc1", | |
| ".encoder.layers.23.mlp.fc2", | |
| "language_model.lm_head", | |
| "language_model.model.layers.0.self_attn.v_proj", | |
| "language_model.model.layers.0.self_attn.o_proj", | |
| "language_model.model.layers.0.self_attn.get_query_key", | |
| "language_model.model.layers.0.mlp.router", | |
| "language_model.model.layers.1.self_attn.v_proj", | |
| "language_model.model.layers.1.self_attn.o_proj", | |
| "language_model.model.layers.1.self_attn.get_query_key", | |
| "language_model.model.layers.1.mlp.router", | |
| "language_model.model.layers.2.self_attn.v_proj", | |
| "language_model.model.layers.2.self_attn.o_proj", | |
| "language_model.model.layers.2.self_attn.get_query_key", | |
| "language_model.model.layers.2.mlp.router", | |
| "language_model.model.layers.3.self_attn.v_proj", | |
| "language_model.model.layers.3.self_attn.o_proj", | |
| "language_model.model.layers.3.self_attn.get_query_key", | |
| "language_model.model.layers.3.mlp.router", | |
| "language_model.model.layers.4.self_attn.v_proj", | |
| "language_model.model.layers.4.self_attn.o_proj", | |
| "language_model.model.layers.4.self_attn.get_query_key", | |
| "language_model.model.layers.4.mlp.router", | |
| "language_model.model.layers.5.self_attn.v_proj", | |
| "language_model.model.layers.5.self_attn.o_proj", | |
| "language_model.model.layers.5.self_attn.get_query_key", | |
| "language_model.model.layers.5.mlp.router", | |
| "language_model.model.layers.6.self_attn.v_proj", | |
| "language_model.model.layers.6.self_attn.o_proj", | |
| "language_model.model.layers.6.self_attn.get_query_key", | |
| "language_model.model.layers.6.mlp.router", | |
| "language_model.model.layers.7.self_attn.v_proj", | |
| "language_model.model.layers.7.self_attn.o_proj", | |
| "language_model.model.layers.7.self_attn.get_query_key", | |
| "language_model.model.layers.7.mlp.router", | |
| "language_model.model.layers.8.self_attn.v_proj", | |
| "language_model.model.layers.8.self_attn.o_proj", | |
| "language_model.model.layers.8.self_attn.get_query_key", | |
| "language_model.model.layers.8.mlp.router", | |
| "language_model.model.layers.9.self_attn.v_proj", | |
| "language_model.model.layers.9.self_attn.o_proj", | |
| "language_model.model.layers.9.self_attn.get_query_key", | |
| "language_model.model.layers.9.mlp.router", | |
| "language_model.model.layers.10.self_attn.v_proj", | |
| "language_model.model.layers.10.self_attn.o_proj", | |
| "language_model.model.layers.10.self_attn.get_query_key", | |
| "language_model.model.layers.10.mlp.router", | |
| "language_model.model.layers.11.self_attn.v_proj", | |
| "language_model.model.layers.11.self_attn.o_proj", | |
| "language_model.model.layers.11.self_attn.get_query_key", | |
| "language_model.model.layers.11.mlp.router", | |
| "language_model.model.layers.12.self_attn.v_proj", | |
| "language_model.model.layers.12.self_attn.o_proj", | |
| "language_model.model.layers.12.self_attn.get_query_key", | |
| "language_model.model.layers.12.mlp.router", | |
| "language_model.model.layers.13.self_attn.v_proj", | |
| "language_model.model.layers.13.self_attn.o_proj", | |
| "language_model.model.layers.13.self_attn.get_query_key", | |
| "language_model.model.layers.13.mlp.router", | |
| "language_model.model.layers.14.self_attn.v_proj", | |
| "language_model.model.layers.14.self_attn.o_proj", | |
| "language_model.model.layers.14.self_attn.get_query_key", | |
| "language_model.model.layers.14.mlp.router", | |
| "language_model.model.layers.15.self_attn.v_proj", | |
| "language_model.model.layers.15.self_attn.o_proj", | |
| "language_model.model.layers.15.self_attn.get_query_key", | |
| "language_model.model.layers.15.mlp.router", | |
| "language_model.model.layers.16.self_attn.v_proj", | |
| "language_model.model.layers.16.self_attn.o_proj", | |
| "language_model.model.layers.16.self_attn.get_query_key", | |
| "language_model.model.layers.16.mlp.router", | |
| "language_model.model.layers.17.self_attn.v_proj", | |
| "language_model.model.layers.17.self_attn.o_proj", | |
| "language_model.model.layers.17.self_attn.get_query_key", | |
| "language_model.model.layers.17.mlp.router", | |
| "language_model.model.layers.18.self_attn.v_proj", | |
| "language_model.model.layers.18.self_attn.o_proj", | |
| "language_model.model.layers.18.self_attn.get_query_key", | |
| "language_model.model.layers.18.mlp.router", | |
| "language_model.model.layers.19.self_attn.v_proj", | |
| "language_model.model.layers.19.self_attn.o_proj", | |
| "language_model.model.layers.19.self_attn.get_query_key", | |
| "language_model.model.layers.19.mlp.router", | |
| "language_model.model.layers.20.self_attn.v_proj", | |
| "language_model.model.layers.20.self_attn.o_proj", | |
| "language_model.model.layers.20.self_attn.get_query_key", | |
| "language_model.model.layers.20.mlp.router", | |
| "language_model.model.layers.21.self_attn.v_proj", | |
| "language_model.model.layers.21.self_attn.o_proj", | |
| "language_model.model.layers.21.self_attn.get_query_key", | |
| "language_model.model.layers.21.mlp.router", | |
| "language_model.model.layers.22.self_attn.v_proj", | |
| "language_model.model.layers.22.self_attn.o_proj", | |
| "language_model.model.layers.22.self_attn.get_query_key", | |
| "language_model.model.layers.22.mlp.router", | |
| "language_model.model.layers.23.self_attn.v_proj", | |
| "language_model.model.layers.23.self_attn.o_proj", | |
| "language_model.model.layers.23.self_attn.get_query_key", | |
| "language_model.model.layers.23.mlp.router", | |
| "language_model.model.layers.24.self_attn.v_proj", | |
| "language_model.model.layers.24.self_attn.o_proj", | |
| "language_model.model.layers.24.self_attn.get_query_key", | |
| "language_model.model.layers.24.mlp.router", | |
| "language_model.model.layers.25.self_attn.v_proj", | |
| "language_model.model.layers.25.self_attn.o_proj", | |
| "language_model.model.layers.25.self_attn.get_query_key", | |
| "language_model.model.layers.25.mlp.router", | |
| "language_model.model.layers.26.self_attn.v_proj", | |
| "language_model.model.layers.26.self_attn.o_proj", | |
| "language_model.model.layers.26.self_attn.get_query_key", | |
| "language_model.model.layers.26.mlp.router", | |
| "language_model.model.layers.27.self_attn.v_proj", | |
| "language_model.model.layers.27.self_attn.o_proj", | |
| "language_model.model.layers.27.self_attn.get_query_key", | |
| "language_model.model.layers.27.mlp.router", | |
| "language_model.model.layers.28.self_attn.v_proj", | |
| "language_model.model.layers.28.self_attn.o_proj", | |
| "language_model.model.layers.28.self_attn.get_query_key", | |
| "language_model.model.layers.28.mlp.router", | |
| "language_model.model.layers.29.self_attn.v_proj", | |
| "language_model.model.layers.29.self_attn.o_proj", | |
| "language_model.model.layers.29.self_attn.get_query_key", | |
| "language_model.model.layers.29.mlp.router", | |
| "language_model.model.layers.30.self_attn.v_proj", | |
| "language_model.model.layers.30.self_attn.o_proj", | |
| "language_model.model.layers.30.self_attn.get_query_key", | |
| "language_model.model.layers.30.mlp.router", | |
| "language_model.model.layers.31.self_attn.v_proj", | |
| "language_model.model.layers.31.self_attn.o_proj", | |
| "language_model.model.layers.31.self_attn.get_query_key", | |
| "language_model.model.layers.31.mlp.router", | |
| "language_model.model.layers.32.self_attn.v_proj", | |
| "language_model.model.layers.32.self_attn.o_proj", | |
| "language_model.model.layers.32.self_attn.get_query_key", | |
| "language_model.model.layers.32.mlp.router", | |
| "language_model.model.layers.33.self_attn.v_proj", | |
| "language_model.model.layers.33.self_attn.o_proj", | |
| "language_model.model.layers.33.self_attn.get_query_key", | |
| "language_model.model.layers.33.mlp.router", | |
| "language_model.model.layers.34.self_attn.v_proj", | |
| "language_model.model.layers.34.self_attn.o_proj", | |
| "language_model.model.layers.34.self_attn.get_query_key", | |
| "language_model.model.layers.34.mlp.router", | |
| "language_model.model.layers.35.self_attn.v_proj", | |
| "language_model.model.layers.35.self_attn.o_proj", | |
| "language_model.model.layers.35.self_attn.get_query_key", | |
| "language_model.model.layers.35.mlp.router", | |
| "language_model.model.layers.36.self_attn.v_proj", | |
| "language_model.model.layers.36.self_attn.o_proj", | |
| "language_model.model.layers.36.self_attn.get_query_key", | |
| "language_model.model.layers.36.mlp.router", | |
| "language_model.model.layers.37.self_attn.v_proj", | |
| "language_model.model.layers.37.self_attn.o_proj", | |
| "language_model.model.layers.37.self_attn.get_query_key", | |
| "language_model.model.layers.37.mlp.router", | |
| "language_model.model.layers.38.self_attn.v_proj", | |
| "language_model.model.layers.38.self_attn.o_proj", | |
| "language_model.model.layers.38.self_attn.get_query_key", | |
| "language_model.model.layers.38.mlp.router", | |
| "language_model.model.layers.39.self_attn.v_proj", | |
| "language_model.model.layers.39.self_attn.o_proj", | |
| "language_model.model.layers.39.self_attn.get_query_key", | |
| "language_model.model.layers.39.mlp.router", | |
| "language_model.model.layers.40.self_attn.v_proj", | |
| "language_model.model.layers.40.self_attn.o_proj", | |
| "language_model.model.layers.40.self_attn.get_query_key", | |
| "language_model.model.layers.40.mlp.router", | |
| "language_model.model.layers.41.self_attn.v_proj", | |
| "language_model.model.layers.41.self_attn.o_proj", | |
| "language_model.model.layers.41.self_attn.get_query_key", | |
| "language_model.model.layers.41.mlp.router", | |
| "language_model.model.layers.42.self_attn.v_proj", | |
| "language_model.model.layers.42.self_attn.o_proj", | |
| "language_model.model.layers.42.self_attn.get_query_key", | |
| "language_model.model.layers.42.mlp.router", | |
| "language_model.model.layers.43.self_attn.v_proj", | |
| "language_model.model.layers.43.self_attn.o_proj", | |
| "language_model.model.layers.43.self_attn.get_query_key", | |
| "language_model.model.layers.43.mlp.router", | |
| "language_model.model.layers.44.self_attn.v_proj", | |
| "language_model.model.layers.44.self_attn.o_proj", | |
| "language_model.model.layers.44.self_attn.get_query_key", | |
| "language_model.model.layers.44.mlp.router", | |
| "language_model.model.layers.45.self_attn.v_proj", | |
| "language_model.model.layers.45.self_attn.o_proj", | |
| "language_model.model.layers.45.self_attn.get_query_key", | |
| "language_model.model.layers.45.mlp.router", | |
| "language_model.model.layers.46.self_attn.v_proj", | |
| "language_model.model.layers.46.self_attn.o_proj", | |
| "language_model.model.layers.46.self_attn.get_query_key", | |
| "language_model.model.layers.46.mlp.router", | |
| "language_model.model.layers.47.self_attn.v_proj", | |
| "language_model.model.layers.47.self_attn.o_proj", | |
| "language_model.model.layers.47.self_attn.get_query_key", | |
| "language_model.model.layers.47.mlp.router", | |
| "language_model.model.layers.48.self_attn.v_proj", | |
| "language_model.model.layers.48.self_attn.o_proj", | |
| "language_model.model.layers.48.self_attn.get_query_key", | |
| "language_model.model.layers.48.mlp.router", | |
| "language_model.model.layers.49.self_attn.v_proj", | |
| "language_model.model.layers.49.self_attn.o_proj", | |
| "language_model.model.layers.49.self_attn.get_query_key", | |
| "language_model.model.layers.49.mlp.router", | |
| "language_model.model.layers.50.self_attn.v_proj", | |
| "language_model.model.layers.50.self_attn.o_proj", | |
| "language_model.model.layers.50.self_attn.get_query_key", | |
| "language_model.model.layers.50.mlp.router", | |
| "language_model.model.layers.51.self_attn.v_proj", | |
| "language_model.model.layers.51.self_attn.o_proj", | |
| "language_model.model.layers.51.self_attn.get_query_key", | |
| "language_model.model.layers.51.mlp.router", | |
| "language_model.model.layers.52.self_attn.v_proj", | |
| "language_model.model.layers.52.self_attn.o_proj", | |
| "language_model.model.layers.52.self_attn.get_query_key", | |
| "language_model.model.layers.52.mlp.router", | |
| "language_model.model.layers.53.self_attn.v_proj", | |
| "language_model.model.layers.53.self_attn.o_proj", | |
| "language_model.model.layers.53.self_attn.get_query_key", | |
| "language_model.model.layers.53.mlp.router", | |
| "language_model.model.layers.54.self_attn.v_proj", | |
| "language_model.model.layers.54.self_attn.o_proj", | |
| "language_model.model.layers.54.self_attn.get_query_key", | |
| "language_model.model.layers.54.mlp.router", | |
| "language_model.model.layers.55.self_attn.v_proj", | |
| "language_model.model.layers.55.self_attn.o_proj", | |
| "language_model.model.layers.55.self_attn.get_query_key", | |
| "language_model.model.layers.55.mlp.router", | |
| "language_model.model.layers.56.self_attn.v_proj", | |
| "language_model.model.layers.56.self_attn.o_proj", | |
| "language_model.model.layers.56.self_attn.get_query_key", | |
| "language_model.model.layers.56.mlp.router", | |
| "language_model.model.layers.57.self_attn.v_proj", | |
| "language_model.model.layers.57.self_attn.o_proj", | |
| "language_model.model.layers.57.self_attn.get_query_key", | |
| "language_model.model.layers.57.mlp.router", | |
| "language_model.model.layers.58.self_attn.v_proj", | |
| "language_model.model.layers.58.self_attn.o_proj", | |
| "language_model.model.layers.58.self_attn.get_query_key", | |
| "language_model.model.layers.58.mlp.router", | |
| "language_model.model.layers.59.self_attn.v_proj", | |
| "language_model.model.layers.59.self_attn.o_proj", | |
| "language_model.model.layers.59.self_attn.get_query_key", | |
| "language_model.model.layers.59.mlp.router", | |
| "language_model.model.layers.60.self_attn.v_proj", | |
| "language_model.model.layers.60.self_attn.o_proj", | |
| "language_model.model.layers.60.self_attn.get_query_key", | |
| "language_model.model.layers.60.mlp.router", | |
| "language_model.model.layers.61.self_attn.v_proj", | |
| "language_model.model.layers.61.self_attn.o_proj", | |
| "language_model.model.layers.61.self_attn.get_query_key", | |
| "language_model.model.layers.61.mlp.router", | |
| "language_model.model.layers.62.self_attn.v_proj", | |
| "language_model.model.layers.62.self_attn.o_proj", | |
| "language_model.model.layers.62.self_attn.get_query_key", | |
| "language_model.model.layers.62.mlp.router", | |
| "language_model.model.layers.63.self_attn.v_proj", | |
| "language_model.model.layers.63.self_attn.o_proj", | |
| "language_model.model.layers.63.self_attn.get_query_key", | |
| "language_model.model.layers.63.mlp.router", | |
| "language_model.model.layers.64.self_attn.v_proj", | |
| "language_model.model.layers.64.self_attn.o_proj", | |
| "language_model.model.layers.64.self_attn.get_query_key", | |
| "language_model.model.layers.64.mlp.router", | |
| "language_model.model.layers.65.self_attn.v_proj", | |
| "language_model.model.layers.65.self_attn.o_proj", | |
| "language_model.model.layers.65.self_attn.get_query_key", | |
| "language_model.model.layers.65.mlp.router", | |
| "language_model.model.layers.66.self_attn.v_proj", | |
| "language_model.model.layers.66.self_attn.o_proj", | |
| "language_model.model.layers.66.self_attn.get_query_key", | |
| "language_model.model.layers.66.mlp.router", | |
| "language_model.model.layers.67.self_attn.v_proj", | |
| "language_model.model.layers.67.self_attn.o_proj", | |
| "language_model.model.layers.67.self_attn.get_query_key", | |
| "language_model.model.layers.67.mlp.router", | |
| "language_model.model.layers.68.self_attn.v_proj", | |
| "language_model.model.layers.68.self_attn.o_proj", | |
| "language_model.model.layers.68.self_attn.get_query_key", | |
| "language_model.model.layers.68.mlp.router", | |
| "language_model.model.layers.69.self_attn.v_proj", | |
| "language_model.model.layers.69.self_attn.o_proj", | |
| "language_model.model.layers.69.self_attn.get_query_key", | |
| "language_model.model.layers.69.mlp.router", | |
| "language_model.model.layers.70.self_attn.v_proj", | |
| "language_model.model.layers.70.self_attn.o_proj", | |
| "language_model.model.layers.70.self_attn.get_query_key", | |
| "language_model.model.layers.70.mlp.router", | |
| "language_model.model.layers.71.self_attn.v_proj", | |
| "language_model.model.layers.71.self_attn.o_proj", | |
| "language_model.model.layers.71.self_attn.get_query_key", | |
| "language_model.model.layers.71.mlp.router", | |
| "language_model.model.layers.72.self_attn.v_proj", | |
| "language_model.model.layers.72.self_attn.o_proj", | |
| "language_model.model.layers.72.self_attn.get_query_key", | |
| "language_model.model.layers.72.mlp.router", | |
| "language_model.model.layers.73.self_attn.v_proj", | |
| "language_model.model.layers.73.self_attn.o_proj", | |
| "language_model.model.layers.73.self_attn.get_query_key", | |
| "language_model.model.layers.73.mlp.router", | |
| "language_model.model.layers.74.self_attn.v_proj", | |
| "language_model.model.layers.74.self_attn.o_proj", | |
| "language_model.model.layers.74.self_attn.get_query_key", | |
| "language_model.model.layers.74.mlp.router", | |
| "language_model.model.layers.75.self_attn.v_proj", | |
| "language_model.model.layers.75.self_attn.o_proj", | |
| "language_model.model.layers.75.self_attn.get_query_key", | |
| "language_model.model.layers.75.mlp.router", | |
| "language_model.model.layers.76.self_attn.v_proj", | |
| "language_model.model.layers.76.self_attn.o_proj", | |
| "language_model.model.layers.76.self_attn.get_query_key", | |
| "language_model.model.layers.76.mlp.router", | |
| "language_model.model.layers.77.self_attn.v_proj", | |
| "language_model.model.layers.77.self_attn.o_proj", | |
| "language_model.model.layers.77.self_attn.get_query_key", | |
| "language_model.model.layers.77.mlp.router", | |
| "language_model.model.layers.78.self_attn.v_proj", | |
| "language_model.model.layers.78.self_attn.o_proj", | |
| "language_model.model.layers.78.self_attn.get_query_key", | |
| "language_model.model.layers.78.mlp.router", | |
| "language_model.model.layers.79.self_attn.v_proj", | |
| "language_model.model.layers.79.self_attn.o_proj", | |
| "language_model.model.layers.79.self_attn.get_query_key", | |
| "language_model.model.layers.79.mlp.router", | |
| "language_model.model.layers.80.self_attn.v_proj", | |
| "language_model.model.layers.80.self_attn.o_proj", | |
| "language_model.model.layers.80.self_attn.get_query_key", | |
| "language_model.model.layers.80.mlp.router", | |
| "language_model.model.layers.81.self_attn.v_proj", | |
| "language_model.model.layers.81.self_attn.o_proj", | |
| "language_model.model.layers.81.self_attn.get_query_key", | |
| "language_model.model.layers.81.mlp.router", | |
| "language_model.model.layers.82.self_attn.v_proj", | |
| "language_model.model.layers.82.self_attn.o_proj", | |
| "language_model.model.layers.82.self_attn.get_query_key", | |
| "language_model.model.layers.82.mlp.router", | |
| "language_model.model.layers.83.self_attn.v_proj", | |
| "language_model.model.layers.83.self_attn.o_proj", | |
| "language_model.model.layers.83.self_attn.get_query_key", | |
| "language_model.model.layers.83.mlp.router", | |
| "language_model.model.layers.84.self_attn.v_proj", | |
| "language_model.model.layers.84.self_attn.o_proj", | |
| "language_model.model.layers.84.self_attn.get_query_key", | |
| "language_model.model.layers.84.mlp.router", | |
| "language_model.model.layers.85.self_attn.v_proj", | |
| "language_model.model.layers.85.self_attn.o_proj", | |
| "language_model.model.layers.85.self_attn.get_query_key", | |
| "language_model.model.layers.85.mlp.router", | |
| "language_model.model.layers.86.self_attn.v_proj", | |
| "language_model.model.layers.86.self_attn.o_proj", | |
| "language_model.model.layers.86.self_attn.get_query_key", | |
| "language_model.model.layers.86.mlp.router", | |
| "language_model.model.layers.87.self_attn.v_proj", | |
| "language_model.model.layers.87.self_attn.o_proj", | |
| "language_model.model.layers.87.self_attn.get_query_key", | |
| "language_model.model.layers.87.mlp.router", | |
| "language_model.model.layers.88.self_attn.v_proj", | |
| "language_model.model.layers.88.self_attn.o_proj", | |
| "language_model.model.layers.88.self_attn.get_query_key", | |
| "language_model.model.layers.88.mlp.router", | |
| "language_model.model.layers.89.self_attn.v_proj", | |
| "language_model.model.layers.89.self_attn.o_proj", | |
| "language_model.model.layers.89.self_attn.get_query_key", | |
| "language_model.model.layers.89.mlp.router", | |
| "language_model.model.layers.90.self_attn.v_proj", | |
| "language_model.model.layers.90.self_attn.o_proj", | |
| "language_model.model.layers.90.self_attn.get_query_key", | |
| "language_model.model.layers.90.mlp.router", | |
| "language_model.model.layers.91.self_attn.v_proj", | |
| "language_model.model.layers.91.self_attn.o_proj", | |
| "language_model.model.layers.91.self_attn.get_query_key", | |
| "language_model.model.layers.91.mlp.router", | |
| "language_model.model.layers.92.self_attn.v_proj", | |
| "language_model.model.layers.92.self_attn.o_proj", | |
| "language_model.model.layers.92.self_attn.get_query_key", | |
| "language_model.model.layers.92.mlp.router", | |
| "language_model.model.layers.93.self_attn.v_proj", | |
| "language_model.model.layers.93.self_attn.o_proj", | |
| "language_model.model.layers.93.self_attn.get_query_key", | |
| "language_model.model.layers.93.mlp.router", | |
| "language_model.model.layers.94.self_attn.v_proj", | |
| "language_model.model.layers.94.self_attn.o_proj", | |
| "language_model.model.layers.94.self_attn.get_query_key", | |
| "language_model.model.layers.94.mlp.router", | |
| "language_model.model.layers.95.self_attn.v_proj", | |
| "language_model.model.layers.95.self_attn.o_proj", | |
| "language_model.model.layers.95.self_attn.get_query_key", | |
| "language_model.model.layers.95.mlp.router", | |
| "language_model.model.layers.96.self_attn.v_proj", | |
| "language_model.model.layers.96.self_attn.o_proj", | |
| "language_model.model.layers.96.self_attn.get_query_key", | |
| "language_model.model.layers.96.mlp.router", | |
| "language_model.model.layers.97.self_attn.v_proj", | |
| "language_model.model.layers.97.self_attn.o_proj", | |
| "language_model.model.layers.97.self_attn.get_query_key", | |
| "language_model.model.layers.97.mlp.router", | |
| "language_model.model.layers.98.self_attn.v_proj", | |
| "language_model.model.layers.98.self_attn.o_proj", | |
| "language_model.model.layers.98.self_attn.get_query_key", | |
| "language_model.model.layers.98.mlp.router", | |
| "language_model.model.layers.99.self_attn.v_proj", | |
| "language_model.model.layers.99.self_attn.o_proj", | |
| "language_model.model.layers.99.self_attn.get_query_key", | |
| "language_model.model.layers.99.mlp.router", | |
| "language_model.model.layers.100.self_attn.v_proj", | |
| "language_model.model.layers.100.self_attn.o_proj", | |
| "language_model.model.layers.100.self_attn.get_query_key", | |
| "language_model.model.layers.100.mlp.router", | |
| "language_model.model.layers.101.self_attn.v_proj", | |
| "language_model.model.layers.101.self_attn.o_proj", | |
| "language_model.model.layers.101.self_attn.get_query_key", | |
| "language_model.model.layers.101.mlp.router", | |
| "language_model.model.layers.102.self_attn.v_proj", | |
| "language_model.model.layers.102.self_attn.o_proj", | |
| "language_model.model.layers.102.self_attn.get_query_key", | |
| "language_model.model.layers.102.mlp.router", | |
| "imagemlp.up_proj", | |
| "imagemlp.gate_proj", | |
| "imagemlp.down_proj" | |
| ], | |
| "kv_cache_scheme": null, | |
| "quant_method": "compressed-tensors", | |
| "quantization_status": "compressed", | |
| "sparsity_config": {}, | |
| "transform_config": {}, | |
| "version": "0.11.0" | |
| }, | |
| "select_layer": -1, | |
| "template": "yuan-chat", | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": null, | |
| "use_backbone_lora": 0, | |
| "use_cache": true, | |
| "use_llm_lora": 0, | |
| "use_thumbnail": true, | |
| "vision_config": { | |
| "architectures": [ | |
| "InternVisionModel" | |
| ], | |
| "attention_dropout": 0.0, | |
| "drop_path_rate": 0.0, | |
| "dropout": 0.0, | |
| "hidden_act": "gelu", | |
| "hidden_size": 1024, | |
| "image_size": 448, | |
| "initializer_factor": 1.0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "layer_norm_eps": 1e-06, | |
| "model_type": "intern_vit_6b", | |
| "norm_type": "layer_norm", | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 24, | |
| "patch_size": 14, | |
| "qk_normalization": false, | |
| "qkv_bias": true, | |
| "torch_dtype": "bfloat16", | |
| "use_bfloat16": true, | |
| "use_flash_attn": false | |
| } | |
| } | |