{ "_name_or_path": "/ceph/hdd/staff/charpent/.cache/models1ogh7zr57phyperr", "activation_function": "gelu_new", "architectures": [ "ImpForCausalLM" ], "attention_dropout": 0.0, "attn_pdrop": 0.0, "auto_map": { "AutoConfig": "configuration_imp.ImpConfig", "AutoModelForCausalLM": "modeling_imp.ImpForCausalLM" }, "bos_token_id": 1, "embd_pdrop": 0.0, "eos_token_id": 50295, "freeze_mm_mlp_adapter": false, "hidden_act": "gelu_new", "hidden_size": 2560, "image_aspect_ratio": "square", "image_token": "", "image_token_index": 50296, "img_processor": null, "initializer_range": 0.02, "intermediate_size": 10240, "layer_norm_eps": 1e-05, "max_position_embeddings": 3072, "mm_hidden_size": 1152, "mm_projector_lr": 2e-05, "mm_projector_type": "mlp2x_gelu", "mm_use_im_patch_token": false, "mm_use_im_start_end": false, "mm_vision_select_feature": "patch", "mm_vision_select_layer": -2, "mm_vision_tower": "google/siglip-so400m-patch14-384", "model_type": "imp", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "pad_token_id": 50256, "partial_rotary_factor": 0.4, "qk_layernorm": false, "quantization_config": { "_load_in_4bit": true, "_load_in_8bit": false, "bnb_4bit_compute_dtype": "bfloat16", "bnb_4bit_quant_storage": "uint8", "bnb_4bit_quant_type": "fp4", "bnb_4bit_use_double_quant": false, "llm_int8_enable_fp32_cpu_offload": false, "llm_int8_has_fp16_weight": false, "llm_int8_skip_modules": [ "lm_head" ], "llm_int8_threshold": 6.0, "load_in_4bit": true, "load_in_8bit": false, "quant_method": "bitsandbytes" }, "resid_pdrop": 0.1, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "tokenizer_model_max_length": 3072, "tokenizer_padding_side": "right", "torch_dtype": "float16", "transformers_version": "4.42.4", "use_cache": true, "use_mm_proj": true, "vision_tower_config": { "attention_dropout": 0.0, "attn_implementation": null, "hidden_act": "gelu_pytorch_tanh", "hidden_size": 1152, "image_size": 384, "intermediate_size": 4304, "layer_norm_eps": 1e-06, "model_type": "siglip_vision_model", "num_attention_heads": 16, "num_channels": 3, "num_hidden_layers": 27, "patch_size": 14 }, "vocab_size": 51200 }