| { |
| "architectures": [ |
| "Gemma4ForConditionalGeneration" |
| ], |
| "audio_config": null, |
| "audio_token_id": 258881, |
| "boa_token_id": 256000, |
| "boi_token_id": 255999, |
| "dtype": "bfloat16", |
| "eoa_token_id": 258883, |
| "eoa_token_index": 258883, |
| "eoi_token_id": 258882, |
| "eos_token_id": 106, |
| "image_token_id": 258880, |
| "initializer_range": 0.02, |
| "model_type": "gemma4", |
| "pad_token_id": 0, |
| "text_config": { |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "attention_k_eq_v": true, |
| "bos_token_id": 2, |
| "dtype": "bfloat16", |
| "enable_moe_block": false, |
| "eos_token_id": 1, |
| "expert_intermediate_size": null, |
| "final_logit_softcapping": 30.0, |
| "global_head_dim": 512, |
| "head_dim": 256, |
| "hidden_activation": "gelu_pytorch_tanh", |
| "hidden_size": 5376, |
| "hidden_size_per_layer_input": 0, |
| "initializer_range": 0.02, |
| "intermediate_size": 21504, |
| "layer_types": [ |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "sliding_attention", |
| "full_attention" |
| ], |
| "max_position_embeddings": 262144, |
| "model_type": "gemma4_text", |
| "moe_intermediate_size": null, |
| "num_attention_heads": 32, |
| "num_experts": null, |
| "num_global_key_value_heads": 4, |
| "num_hidden_layers": 60, |
| "num_key_value_heads": 16, |
| "num_kv_shared_layers": 0, |
| "pad_token_id": 0, |
| "rms_norm_eps": 1e-06, |
| "rope_parameters": { |
| "full_attention": { |
| "partial_rotary_factor": 0.25, |
| "rope_theta": 1000000.0, |
| "rope_type": "proportional" |
| }, |
| "sliding_attention": { |
| "rope_theta": 10000.0, |
| "rope_type": "default" |
| } |
| }, |
| "sliding_window": 1024, |
| "tie_word_embeddings": false, |
| "top_k_experts": null, |
| "use_bidirectional_attention": "vision", |
| "use_cache": true, |
| "use_double_wide_mlp": false, |
| "vocab_size": 262144, |
| "vocab_size_per_layer_input": 262144 |
| }, |
| "tie_word_embeddings": false, |
| "transformers_version": "5.13.0.dev0", |
| "unsloth_fixed": true, |
| "video_token_id": 258884, |
| "vision_config": { |
| "_name_or_path": "", |
| "architectures": null, |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "chunk_size_feed_forward": 0, |
| "default_output_length": 280, |
| "dtype": "bfloat16", |
| "global_head_dim": 72, |
| "head_dim": 72, |
| "hidden_activation": "gelu_pytorch_tanh", |
| "hidden_size": 1152, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 4304, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "max_position_embeddings": 131072, |
| "model_type": "gemma4_vision", |
| "num_attention_heads": 16, |
| "num_hidden_layers": 27, |
| "num_key_value_heads": 16, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "patch_size": 16, |
| "pooling_kernel_size": 3, |
| "position_embedding_size": 10240, |
| "problem_type": null, |
| "return_dict": true, |
| "rms_norm_eps": 1e-06, |
| "rope_parameters": { |
| "rope_theta": 100.0, |
| "rope_type": "default" |
| }, |
| "standardize": true, |
| "use_clipped_linears": false |
| }, |
| "vision_soft_tokens_per_image": 280, |
| "quantization_config": { |
| "quant_method": "compressed-tensors", |
| "format": "float-quantized", |
| "config_groups": { |
| "group_0": { |
| "weights": { |
| "num_bits": 8, |
| "type": "float", |
| "symmetric": true, |
| "strategy": "channel", |
| "dynamic": false |
| }, |
| "input_activations": null, |
| "targets": [ |
| "Linear" |
| ] |
| } |
| }, |
| "ignore": [ |
| "lm_head", |
| "model.embed_vision.embedding_projection", |
| "model.language_model.embed_tokens", |
| "model.language_model.layers.0.input_layernorm", |
| "model.language_model.layers.0.layer_scalar", |
| "model.language_model.layers.0.post_attention_layernorm", |
| "model.language_model.layers.0.post_feedforward_layernorm", |
| "model.language_model.layers.0.pre_feedforward_layernorm", |
| "model.language_model.layers.0.self_attn.k_norm", |
| "model.language_model.layers.0.self_attn.q_norm", |
| "model.language_model.layers.1.input_layernorm", |
| "model.language_model.layers.1.layer_scalar", |
| "model.language_model.layers.1.post_attention_layernorm", |
| "model.language_model.layers.1.post_feedforward_layernorm", |
| "model.language_model.layers.1.pre_feedforward_layernorm", |
| "model.language_model.layers.1.self_attn.k_norm", |
| "model.language_model.layers.1.self_attn.q_norm", |
| "model.language_model.layers.10.input_layernorm", |
| "model.language_model.layers.10.layer_scalar", |
| "model.language_model.layers.10.post_attention_layernorm", |
| "model.language_model.layers.10.post_feedforward_layernorm", |
| "model.language_model.layers.10.pre_feedforward_layernorm", |
| "model.language_model.layers.10.self_attn.k_norm", |
| "model.language_model.layers.10.self_attn.q_norm", |
| "model.language_model.layers.11.input_layernorm", |
| "model.language_model.layers.11.layer_scalar", |
| "model.language_model.layers.11.post_attention_layernorm", |
| "model.language_model.layers.11.post_feedforward_layernorm", |
| "model.language_model.layers.11.pre_feedforward_layernorm", |
| "model.language_model.layers.11.self_attn.k_norm", |
| "model.language_model.layers.11.self_attn.q_norm", |
| "model.language_model.layers.12.input_layernorm", |
| "model.language_model.layers.12.layer_scalar", |
| "model.language_model.layers.12.post_attention_layernorm", |
| "model.language_model.layers.12.post_feedforward_layernorm", |
| "model.language_model.layers.12.pre_feedforward_layernorm", |
| "model.language_model.layers.12.self_attn.k_norm", |
| "model.language_model.layers.12.self_attn.q_norm", |
| "model.language_model.layers.13.input_layernorm", |
| "model.language_model.layers.13.layer_scalar", |
| "model.language_model.layers.13.post_attention_layernorm", |
| "model.language_model.layers.13.post_feedforward_layernorm", |
| "model.language_model.layers.13.pre_feedforward_layernorm", |
| "model.language_model.layers.13.self_attn.k_norm", |
| "model.language_model.layers.13.self_attn.q_norm", |
| "model.language_model.layers.14.input_layernorm", |
| "model.language_model.layers.14.layer_scalar", |
| "model.language_model.layers.14.post_attention_layernorm", |
| "model.language_model.layers.14.post_feedforward_layernorm", |
| "model.language_model.layers.14.pre_feedforward_layernorm", |
| "model.language_model.layers.14.self_attn.k_norm", |
| "model.language_model.layers.14.self_attn.q_norm", |
| "model.language_model.layers.15.input_layernorm", |
| "model.language_model.layers.15.layer_scalar", |
| "model.language_model.layers.15.post_attention_layernorm", |
| "model.language_model.layers.15.post_feedforward_layernorm", |
| "model.language_model.layers.15.pre_feedforward_layernorm", |
| "model.language_model.layers.15.self_attn.k_norm", |
| "model.language_model.layers.15.self_attn.q_norm", |
| "model.language_model.layers.16.input_layernorm", |
| "model.language_model.layers.16.layer_scalar", |
| "model.language_model.layers.16.post_attention_layernorm", |
| "model.language_model.layers.16.post_feedforward_layernorm", |
| "model.language_model.layers.16.pre_feedforward_layernorm", |
| "model.language_model.layers.16.self_attn.k_norm", |
| "model.language_model.layers.16.self_attn.q_norm", |
| "model.language_model.layers.17.input_layernorm", |
| "model.language_model.layers.17.layer_scalar", |
| "model.language_model.layers.17.post_attention_layernorm", |
| "model.language_model.layers.17.post_feedforward_layernorm", |
| "model.language_model.layers.17.pre_feedforward_layernorm", |
| "model.language_model.layers.17.self_attn.k_norm", |
| "model.language_model.layers.17.self_attn.q_norm", |
| "model.language_model.layers.18.input_layernorm", |
| "model.language_model.layers.18.layer_scalar", |
| "model.language_model.layers.18.post_attention_layernorm", |
| "model.language_model.layers.18.post_feedforward_layernorm", |
| "model.language_model.layers.18.pre_feedforward_layernorm", |
| "model.language_model.layers.18.self_attn.k_norm", |
| "model.language_model.layers.18.self_attn.q_norm", |
| "model.language_model.layers.19.input_layernorm", |
| "model.language_model.layers.19.layer_scalar", |
| "model.language_model.layers.19.post_attention_layernorm", |
| "model.language_model.layers.19.post_feedforward_layernorm", |
| "model.language_model.layers.19.pre_feedforward_layernorm", |
| "model.language_model.layers.19.self_attn.k_norm", |
| "model.language_model.layers.19.self_attn.q_norm", |
| "model.language_model.layers.2.input_layernorm", |
| "model.language_model.layers.2.layer_scalar", |
| "model.language_model.layers.2.post_attention_layernorm", |
| "model.language_model.layers.2.post_feedforward_layernorm", |
| "model.language_model.layers.2.pre_feedforward_layernorm", |
| "model.language_model.layers.2.self_attn.k_norm", |
| "model.language_model.layers.2.self_attn.q_norm", |
| "model.language_model.layers.20.input_layernorm", |
| "model.language_model.layers.20.layer_scalar", |
| "model.language_model.layers.20.post_attention_layernorm", |
| "model.language_model.layers.20.post_feedforward_layernorm", |
| "model.language_model.layers.20.pre_feedforward_layernorm", |
| "model.language_model.layers.20.self_attn.k_norm", |
| "model.language_model.layers.20.self_attn.q_norm", |
| "model.language_model.layers.21.input_layernorm", |
| "model.language_model.layers.21.layer_scalar", |
| "model.language_model.layers.21.post_attention_layernorm", |
| "model.language_model.layers.21.post_feedforward_layernorm", |
| "model.language_model.layers.21.pre_feedforward_layernorm", |
| "model.language_model.layers.21.self_attn.k_norm", |
| "model.language_model.layers.21.self_attn.q_norm", |
| "model.language_model.layers.22.input_layernorm", |
| "model.language_model.layers.22.layer_scalar", |
| "model.language_model.layers.22.post_attention_layernorm", |
| "model.language_model.layers.22.post_feedforward_layernorm", |
| "model.language_model.layers.22.pre_feedforward_layernorm", |
| "model.language_model.layers.22.self_attn.k_norm", |
| "model.language_model.layers.22.self_attn.q_norm", |
| "model.language_model.layers.23.input_layernorm", |
| "model.language_model.layers.23.layer_scalar", |
| "model.language_model.layers.23.post_attention_layernorm", |
| "model.language_model.layers.23.post_feedforward_layernorm", |
| "model.language_model.layers.23.pre_feedforward_layernorm", |
| "model.language_model.layers.23.self_attn.k_norm", |
| "model.language_model.layers.23.self_attn.q_norm", |
| "model.language_model.layers.24.input_layernorm", |
| "model.language_model.layers.24.layer_scalar", |
| "model.language_model.layers.24.post_attention_layernorm", |
| "model.language_model.layers.24.post_feedforward_layernorm", |
| "model.language_model.layers.24.pre_feedforward_layernorm", |
| "model.language_model.layers.24.self_attn.k_norm", |
| "model.language_model.layers.24.self_attn.q_norm", |
| "model.language_model.layers.25.input_layernorm", |
| "model.language_model.layers.25.layer_scalar", |
| "model.language_model.layers.25.post_attention_layernorm", |
| "model.language_model.layers.25.post_feedforward_layernorm", |
| "model.language_model.layers.25.pre_feedforward_layernorm", |
| "model.language_model.layers.25.self_attn.k_norm", |
| "model.language_model.layers.25.self_attn.q_norm", |
| "model.language_model.layers.26.input_layernorm", |
| "model.language_model.layers.26.layer_scalar", |
| "model.language_model.layers.26.post_attention_layernorm", |
| "model.language_model.layers.26.post_feedforward_layernorm", |
| "model.language_model.layers.26.pre_feedforward_layernorm", |
| "model.language_model.layers.26.self_attn.k_norm", |
| "model.language_model.layers.26.self_attn.q_norm", |
| "model.language_model.layers.27.input_layernorm", |
| "model.language_model.layers.27.layer_scalar", |
| "model.language_model.layers.27.post_attention_layernorm", |
| "model.language_model.layers.27.post_feedforward_layernorm", |
| "model.language_model.layers.27.pre_feedforward_layernorm", |
| "model.language_model.layers.27.self_attn.k_norm", |
| "model.language_model.layers.27.self_attn.q_norm", |
| "model.language_model.layers.28.input_layernorm", |
| "model.language_model.layers.28.layer_scalar", |
| "model.language_model.layers.28.post_attention_layernorm", |
| "model.language_model.layers.28.post_feedforward_layernorm", |
| "model.language_model.layers.28.pre_feedforward_layernorm", |
| "model.language_model.layers.28.self_attn.k_norm", |
| "model.language_model.layers.28.self_attn.q_norm", |
| "model.language_model.layers.29.input_layernorm", |
| "model.language_model.layers.29.layer_scalar", |
| "model.language_model.layers.29.post_attention_layernorm", |
| "model.language_model.layers.29.post_feedforward_layernorm", |
| "model.language_model.layers.29.pre_feedforward_layernorm", |
| "model.language_model.layers.29.self_attn.k_norm", |
| "model.language_model.layers.29.self_attn.q_norm", |
| "model.language_model.layers.3.input_layernorm", |
| "model.language_model.layers.3.layer_scalar", |
| "model.language_model.layers.3.post_attention_layernorm", |
| "model.language_model.layers.3.post_feedforward_layernorm", |
| "model.language_model.layers.3.pre_feedforward_layernorm", |
| "model.language_model.layers.3.self_attn.k_norm", |
| "model.language_model.layers.3.self_attn.q_norm", |
| "model.language_model.layers.30.input_layernorm", |
| "model.language_model.layers.30.layer_scalar", |
| "model.language_model.layers.30.post_attention_layernorm", |
| "model.language_model.layers.30.post_feedforward_layernorm", |
| "model.language_model.layers.30.pre_feedforward_layernorm", |
| "model.language_model.layers.30.self_attn.k_norm", |
| "model.language_model.layers.30.self_attn.q_norm", |
| "model.language_model.layers.31.input_layernorm", |
| "model.language_model.layers.31.layer_scalar", |
| "model.language_model.layers.31.post_attention_layernorm", |
| "model.language_model.layers.31.post_feedforward_layernorm", |
| "model.language_model.layers.31.pre_feedforward_layernorm", |
| "model.language_model.layers.31.self_attn.k_norm", |
| "model.language_model.layers.31.self_attn.q_norm", |
| "model.language_model.layers.32.input_layernorm", |
| "model.language_model.layers.32.layer_scalar", |
| "model.language_model.layers.32.post_attention_layernorm", |
| "model.language_model.layers.32.post_feedforward_layernorm", |
| "model.language_model.layers.32.pre_feedforward_layernorm", |
| "model.language_model.layers.32.self_attn.k_norm", |
| "model.language_model.layers.32.self_attn.q_norm", |
| "model.language_model.layers.33.input_layernorm", |
| "model.language_model.layers.33.layer_scalar", |
| "model.language_model.layers.33.post_attention_layernorm", |
| "model.language_model.layers.33.post_feedforward_layernorm", |
| "model.language_model.layers.33.pre_feedforward_layernorm", |
| "model.language_model.layers.33.self_attn.k_norm", |
| "model.language_model.layers.33.self_attn.q_norm", |
| "model.language_model.layers.34.input_layernorm", |
| "model.language_model.layers.34.layer_scalar", |
| "model.language_model.layers.34.post_attention_layernorm", |
| "model.language_model.layers.34.post_feedforward_layernorm", |
| "model.language_model.layers.34.pre_feedforward_layernorm", |
| "model.language_model.layers.34.self_attn.k_norm", |
| "model.language_model.layers.34.self_attn.q_norm", |
| "model.language_model.layers.35.input_layernorm", |
| "model.language_model.layers.35.layer_scalar", |
| "model.language_model.layers.35.post_attention_layernorm", |
| "model.language_model.layers.35.post_feedforward_layernorm", |
| "model.language_model.layers.35.pre_feedforward_layernorm", |
| "model.language_model.layers.35.self_attn.k_norm", |
| "model.language_model.layers.35.self_attn.q_norm", |
| "model.language_model.layers.36.input_layernorm", |
| "model.language_model.layers.36.layer_scalar", |
| "model.language_model.layers.36.post_attention_layernorm", |
| "model.language_model.layers.36.post_feedforward_layernorm", |
| "model.language_model.layers.36.pre_feedforward_layernorm", |
| "model.language_model.layers.36.self_attn.k_norm", |
| "model.language_model.layers.36.self_attn.q_norm", |
| "model.language_model.layers.37.input_layernorm", |
| "model.language_model.layers.37.layer_scalar", |
| "model.language_model.layers.37.post_attention_layernorm", |
| "model.language_model.layers.37.post_feedforward_layernorm", |
| "model.language_model.layers.37.pre_feedforward_layernorm", |
| "model.language_model.layers.37.self_attn.k_norm", |
| "model.language_model.layers.37.self_attn.q_norm", |
| "model.language_model.layers.38.input_layernorm", |
| "model.language_model.layers.38.layer_scalar", |
| "model.language_model.layers.38.post_attention_layernorm", |
| "model.language_model.layers.38.post_feedforward_layernorm", |
| "model.language_model.layers.38.pre_feedforward_layernorm", |
| "model.language_model.layers.38.self_attn.k_norm", |
| "model.language_model.layers.38.self_attn.q_norm", |
| "model.language_model.layers.39.input_layernorm", |
| "model.language_model.layers.39.layer_scalar", |
| "model.language_model.layers.39.post_attention_layernorm", |
| "model.language_model.layers.39.post_feedforward_layernorm", |
| "model.language_model.layers.39.pre_feedforward_layernorm", |
| "model.language_model.layers.39.self_attn.k_norm", |
| "model.language_model.layers.39.self_attn.q_norm", |
| "model.language_model.layers.4.input_layernorm", |
| "model.language_model.layers.4.layer_scalar", |
| "model.language_model.layers.4.post_attention_layernorm", |
| "model.language_model.layers.4.post_feedforward_layernorm", |
| "model.language_model.layers.4.pre_feedforward_layernorm", |
| "model.language_model.layers.4.self_attn.k_norm", |
| "model.language_model.layers.4.self_attn.q_norm", |
| "model.language_model.layers.40.input_layernorm", |
| "model.language_model.layers.40.layer_scalar", |
| "model.language_model.layers.40.post_attention_layernorm", |
| "model.language_model.layers.40.post_feedforward_layernorm", |
| "model.language_model.layers.40.pre_feedforward_layernorm", |
| "model.language_model.layers.40.self_attn.k_norm", |
| "model.language_model.layers.40.self_attn.q_norm", |
| "model.language_model.layers.41.input_layernorm", |
| "model.language_model.layers.41.layer_scalar", |
| "model.language_model.layers.41.post_attention_layernorm", |
| "model.language_model.layers.41.post_feedforward_layernorm", |
| "model.language_model.layers.41.pre_feedforward_layernorm", |
| "model.language_model.layers.41.self_attn.k_norm", |
| "model.language_model.layers.41.self_attn.q_norm", |
| "model.language_model.layers.42.input_layernorm", |
| "model.language_model.layers.42.layer_scalar", |
| "model.language_model.layers.42.post_attention_layernorm", |
| "model.language_model.layers.42.post_feedforward_layernorm", |
| "model.language_model.layers.42.pre_feedforward_layernorm", |
| "model.language_model.layers.42.self_attn.k_norm", |
| "model.language_model.layers.42.self_attn.q_norm", |
| "model.language_model.layers.43.input_layernorm", |
| "model.language_model.layers.43.layer_scalar", |
| "model.language_model.layers.43.post_attention_layernorm", |
| "model.language_model.layers.43.post_feedforward_layernorm", |
| "model.language_model.layers.43.pre_feedforward_layernorm", |
| "model.language_model.layers.43.self_attn.k_norm", |
| "model.language_model.layers.43.self_attn.q_norm", |
| "model.language_model.layers.44.input_layernorm", |
| "model.language_model.layers.44.layer_scalar", |
| "model.language_model.layers.44.post_attention_layernorm", |
| "model.language_model.layers.44.post_feedforward_layernorm", |
| "model.language_model.layers.44.pre_feedforward_layernorm", |
| "model.language_model.layers.44.self_attn.k_norm", |
| "model.language_model.layers.44.self_attn.q_norm", |
| "model.language_model.layers.45.input_layernorm", |
| "model.language_model.layers.45.layer_scalar", |
| "model.language_model.layers.45.post_attention_layernorm", |
| "model.language_model.layers.45.post_feedforward_layernorm", |
| "model.language_model.layers.45.pre_feedforward_layernorm", |
| "model.language_model.layers.45.self_attn.k_norm", |
| "model.language_model.layers.45.self_attn.q_norm", |
| "model.language_model.layers.46.input_layernorm", |
| "model.language_model.layers.46.layer_scalar", |
| "model.language_model.layers.46.post_attention_layernorm", |
| "model.language_model.layers.46.post_feedforward_layernorm", |
| "model.language_model.layers.46.pre_feedforward_layernorm", |
| "model.language_model.layers.46.self_attn.k_norm", |
| "model.language_model.layers.46.self_attn.q_norm", |
| "model.language_model.layers.47.input_layernorm", |
| "model.language_model.layers.47.layer_scalar", |
| "model.language_model.layers.47.post_attention_layernorm", |
| "model.language_model.layers.47.post_feedforward_layernorm", |
| "model.language_model.layers.47.pre_feedforward_layernorm", |
| "model.language_model.layers.47.self_attn.k_norm", |
| "model.language_model.layers.47.self_attn.q_norm", |
| "model.language_model.layers.48.input_layernorm", |
| "model.language_model.layers.48.layer_scalar", |
| "model.language_model.layers.48.post_attention_layernorm", |
| "model.language_model.layers.48.post_feedforward_layernorm", |
| "model.language_model.layers.48.pre_feedforward_layernorm", |
| "model.language_model.layers.48.self_attn.k_norm", |
| "model.language_model.layers.48.self_attn.q_norm", |
| "model.language_model.layers.49.input_layernorm", |
| "model.language_model.layers.49.layer_scalar", |
| "model.language_model.layers.49.post_attention_layernorm", |
| "model.language_model.layers.49.post_feedforward_layernorm", |
| "model.language_model.layers.49.pre_feedforward_layernorm", |
| "model.language_model.layers.49.self_attn.k_norm", |
| "model.language_model.layers.49.self_attn.q_norm", |
| "model.language_model.layers.5.input_layernorm", |
| "model.language_model.layers.5.layer_scalar", |
| "model.language_model.layers.5.post_attention_layernorm", |
| "model.language_model.layers.5.post_feedforward_layernorm", |
| "model.language_model.layers.5.pre_feedforward_layernorm", |
| "model.language_model.layers.5.self_attn.k_norm", |
| "model.language_model.layers.5.self_attn.q_norm", |
| "model.language_model.layers.50.input_layernorm", |
| "model.language_model.layers.50.layer_scalar", |
| "model.language_model.layers.50.post_attention_layernorm", |
| "model.language_model.layers.50.post_feedforward_layernorm", |
| "model.language_model.layers.50.pre_feedforward_layernorm", |
| "model.language_model.layers.50.self_attn.k_norm", |
| "model.language_model.layers.50.self_attn.q_norm", |
| "model.language_model.layers.51.input_layernorm", |
| "model.language_model.layers.51.layer_scalar", |
| "model.language_model.layers.51.post_attention_layernorm", |
| "model.language_model.layers.51.post_feedforward_layernorm", |
| "model.language_model.layers.51.pre_feedforward_layernorm", |
| "model.language_model.layers.51.self_attn.k_norm", |
| "model.language_model.layers.51.self_attn.q_norm", |
| "model.language_model.layers.52.input_layernorm", |
| "model.language_model.layers.52.layer_scalar", |
| "model.language_model.layers.52.post_attention_layernorm", |
| "model.language_model.layers.52.post_feedforward_layernorm", |
| "model.language_model.layers.52.pre_feedforward_layernorm", |
| "model.language_model.layers.52.self_attn.k_norm", |
| "model.language_model.layers.52.self_attn.q_norm", |
| "model.language_model.layers.53.input_layernorm", |
| "model.language_model.layers.53.layer_scalar", |
| "model.language_model.layers.53.post_attention_layernorm", |
| "model.language_model.layers.53.post_feedforward_layernorm", |
| "model.language_model.layers.53.pre_feedforward_layernorm", |
| "model.language_model.layers.53.self_attn.k_norm", |
| "model.language_model.layers.53.self_attn.q_norm", |
| "model.language_model.layers.54.input_layernorm", |
| "model.language_model.layers.54.layer_scalar", |
| "model.language_model.layers.54.post_attention_layernorm", |
| "model.language_model.layers.54.post_feedforward_layernorm", |
| "model.language_model.layers.54.pre_feedforward_layernorm", |
| "model.language_model.layers.54.self_attn.k_norm", |
| "model.language_model.layers.54.self_attn.q_norm", |
| "model.language_model.layers.55.input_layernorm", |
| "model.language_model.layers.55.layer_scalar", |
| "model.language_model.layers.55.post_attention_layernorm", |
| "model.language_model.layers.55.post_feedforward_layernorm", |
| "model.language_model.layers.55.pre_feedforward_layernorm", |
| "model.language_model.layers.55.self_attn.k_norm", |
| "model.language_model.layers.55.self_attn.q_norm", |
| "model.language_model.layers.56.input_layernorm", |
| "model.language_model.layers.56.layer_scalar", |
| "model.language_model.layers.56.post_attention_layernorm", |
| "model.language_model.layers.56.post_feedforward_layernorm", |
| "model.language_model.layers.56.pre_feedforward_layernorm", |
| "model.language_model.layers.56.self_attn.k_norm", |
| "model.language_model.layers.56.self_attn.q_norm", |
| "model.language_model.layers.57.input_layernorm", |
| "model.language_model.layers.57.layer_scalar", |
| "model.language_model.layers.57.post_attention_layernorm", |
| "model.language_model.layers.57.post_feedforward_layernorm", |
| "model.language_model.layers.57.pre_feedforward_layernorm", |
| "model.language_model.layers.57.self_attn.k_norm", |
| "model.language_model.layers.57.self_attn.q_norm", |
| "model.language_model.layers.58.input_layernorm", |
| "model.language_model.layers.58.layer_scalar", |
| "model.language_model.layers.58.post_attention_layernorm", |
| "model.language_model.layers.58.post_feedforward_layernorm", |
| "model.language_model.layers.58.pre_feedforward_layernorm", |
| "model.language_model.layers.58.self_attn.k_norm", |
| "model.language_model.layers.58.self_attn.q_norm", |
| "model.language_model.layers.59.input_layernorm", |
| "model.language_model.layers.59.layer_scalar", |
| "model.language_model.layers.59.post_attention_layernorm", |
| "model.language_model.layers.59.post_feedforward_layernorm", |
| "model.language_model.layers.59.pre_feedforward_layernorm", |
| "model.language_model.layers.59.self_attn.k_norm", |
| "model.language_model.layers.59.self_attn.q_norm", |
| "model.language_model.layers.6.input_layernorm", |
| "model.language_model.layers.6.layer_scalar", |
| "model.language_model.layers.6.post_attention_layernorm", |
| "model.language_model.layers.6.post_feedforward_layernorm", |
| "model.language_model.layers.6.pre_feedforward_layernorm", |
| "model.language_model.layers.6.self_attn.k_norm", |
| "model.language_model.layers.6.self_attn.q_norm", |
| "model.language_model.layers.7.input_layernorm", |
| "model.language_model.layers.7.layer_scalar", |
| "model.language_model.layers.7.post_attention_layernorm", |
| "model.language_model.layers.7.post_feedforward_layernorm", |
| "model.language_model.layers.7.pre_feedforward_layernorm", |
| "model.language_model.layers.7.self_attn.k_norm", |
| "model.language_model.layers.7.self_attn.q_norm", |
| "model.language_model.layers.8.input_layernorm", |
| "model.language_model.layers.8.layer_scalar", |
| "model.language_model.layers.8.post_attention_layernorm", |
| "model.language_model.layers.8.post_feedforward_layernorm", |
| "model.language_model.layers.8.pre_feedforward_layernorm", |
| "model.language_model.layers.8.self_attn.k_norm", |
| "model.language_model.layers.8.self_attn.q_norm", |
| "model.language_model.layers.9.input_layernorm", |
| "model.language_model.layers.9.layer_scalar", |
| "model.language_model.layers.9.post_attention_layernorm", |
| "model.language_model.layers.9.post_feedforward_layernorm", |
| "model.language_model.layers.9.pre_feedforward_layernorm", |
| "model.language_model.layers.9.self_attn.k_norm", |
| "model.language_model.layers.9.self_attn.q_norm", |
| "model.language_model.norm", |
| "model.vision_tower.encoder.layers.0.input_layernorm", |
| "model.vision_tower.encoder.layers.0.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.0.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.0.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.0.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.0.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.0.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.0.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.0.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.0.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.0.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.0.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.0.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.1.input_layernorm", |
| "model.vision_tower.encoder.layers.1.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.1.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.1.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.1.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.1.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.1.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.1.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.1.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.1.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.1.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.1.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.1.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.10.input_layernorm", |
| "model.vision_tower.encoder.layers.10.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.10.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.10.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.10.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.10.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.10.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.10.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.10.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.10.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.10.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.10.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.10.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.11.input_layernorm", |
| "model.vision_tower.encoder.layers.11.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.11.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.11.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.11.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.11.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.11.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.11.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.11.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.11.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.11.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.11.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.11.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.12.input_layernorm", |
| "model.vision_tower.encoder.layers.12.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.12.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.12.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.12.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.12.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.12.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.12.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.12.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.12.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.12.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.12.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.12.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.13.input_layernorm", |
| "model.vision_tower.encoder.layers.13.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.13.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.13.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.13.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.13.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.13.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.13.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.13.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.13.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.13.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.13.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.13.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.14.input_layernorm", |
| "model.vision_tower.encoder.layers.14.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.14.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.14.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.14.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.14.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.14.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.14.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.14.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.14.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.14.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.14.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.14.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.15.input_layernorm", |
| "model.vision_tower.encoder.layers.15.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.15.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.15.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.15.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.15.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.15.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.15.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.15.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.15.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.15.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.15.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.15.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.16.input_layernorm", |
| "model.vision_tower.encoder.layers.16.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.16.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.16.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.16.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.16.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.16.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.16.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.16.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.16.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.16.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.16.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.16.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.17.input_layernorm", |
| "model.vision_tower.encoder.layers.17.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.17.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.17.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.17.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.17.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.17.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.17.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.17.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.17.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.17.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.17.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.17.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.18.input_layernorm", |
| "model.vision_tower.encoder.layers.18.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.18.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.18.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.18.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.18.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.18.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.18.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.18.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.18.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.18.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.18.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.18.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.19.input_layernorm", |
| "model.vision_tower.encoder.layers.19.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.19.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.19.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.19.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.19.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.19.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.19.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.19.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.19.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.19.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.19.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.19.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.2.input_layernorm", |
| "model.vision_tower.encoder.layers.2.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.2.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.2.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.2.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.2.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.2.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.2.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.2.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.2.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.2.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.2.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.2.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.20.input_layernorm", |
| "model.vision_tower.encoder.layers.20.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.20.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.20.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.20.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.20.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.20.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.20.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.20.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.20.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.20.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.20.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.20.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.21.input_layernorm", |
| "model.vision_tower.encoder.layers.21.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.21.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.21.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.21.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.21.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.21.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.21.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.21.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.21.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.21.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.21.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.21.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.22.input_layernorm", |
| "model.vision_tower.encoder.layers.22.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.22.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.22.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.22.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.22.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.22.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.22.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.22.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.22.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.22.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.22.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.22.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.23.input_layernorm", |
| "model.vision_tower.encoder.layers.23.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.23.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.23.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.23.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.23.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.23.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.23.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.23.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.23.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.23.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.23.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.23.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.24.input_layernorm", |
| "model.vision_tower.encoder.layers.24.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.24.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.24.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.24.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.24.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.24.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.24.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.24.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.24.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.24.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.24.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.24.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.25.input_layernorm", |
| "model.vision_tower.encoder.layers.25.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.25.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.25.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.25.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.25.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.25.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.25.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.25.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.25.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.25.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.25.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.25.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.26.input_layernorm", |
| "model.vision_tower.encoder.layers.26.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.26.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.26.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.26.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.26.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.26.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.26.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.26.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.26.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.26.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.26.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.26.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.3.input_layernorm", |
| "model.vision_tower.encoder.layers.3.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.3.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.3.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.3.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.3.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.3.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.3.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.3.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.3.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.3.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.3.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.3.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.4.input_layernorm", |
| "model.vision_tower.encoder.layers.4.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.4.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.4.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.4.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.4.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.4.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.4.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.4.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.4.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.4.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.4.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.4.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.5.input_layernorm", |
| "model.vision_tower.encoder.layers.5.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.5.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.5.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.5.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.5.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.5.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.5.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.5.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.5.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.5.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.5.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.5.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.6.input_layernorm", |
| "model.vision_tower.encoder.layers.6.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.6.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.6.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.6.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.6.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.6.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.6.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.6.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.6.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.6.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.6.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.6.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.7.input_layernorm", |
| "model.vision_tower.encoder.layers.7.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.7.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.7.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.7.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.7.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.7.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.7.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.7.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.7.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.7.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.7.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.7.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.8.input_layernorm", |
| "model.vision_tower.encoder.layers.8.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.8.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.8.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.8.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.8.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.8.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.8.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.8.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.8.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.8.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.8.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.8.self_attn.v_proj.linear", |
| "model.vision_tower.encoder.layers.9.input_layernorm", |
| "model.vision_tower.encoder.layers.9.mlp.down_proj.linear", |
| "model.vision_tower.encoder.layers.9.mlp.gate_proj.linear", |
| "model.vision_tower.encoder.layers.9.mlp.up_proj.linear", |
| "model.vision_tower.encoder.layers.9.post_attention_layernorm", |
| "model.vision_tower.encoder.layers.9.post_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.9.pre_feedforward_layernorm", |
| "model.vision_tower.encoder.layers.9.self_attn.k_norm", |
| "model.vision_tower.encoder.layers.9.self_attn.k_proj.linear", |
| "model.vision_tower.encoder.layers.9.self_attn.o_proj.linear", |
| "model.vision_tower.encoder.layers.9.self_attn.q_norm", |
| "model.vision_tower.encoder.layers.9.self_attn.q_proj.linear", |
| "model.vision_tower.encoder.layers.9.self_attn.v_proj.linear", |
| "model.vision_tower.patch_embedder.input_proj", |
| "model.vision_tower.patch_embedder.position_embedding_table", |
| "model.vision_tower.std_bias", |
| "model.vision_tower.std_scale" |
| ], |
| "kv_cache_scheme": null |
| } |
| } |
