| { | |
| "_name_or_path": "/ceph/hdd/staff/charpent/.cache/models2riyr4wgy2r4vryo", | |
| "architectures": [ | |
| "TinyLlavaForConditionalGeneration" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration.TinyLlavaConfig", | |
| "AutoModelForCausalLM": "modeling_tinyllava_phi.TinyLlavaForConditionalGeneration" | |
| }, | |
| "cache_dir": null, | |
| "connector_type": "mlp2x_gelu", | |
| "hidden_size": 2560, | |
| "ignore_index": -100, | |
| "image_aspect_ratio": "square", | |
| "image_token_index": -200, | |
| "llm_model_name_or_path": "microsoft/phi-2", | |
| "model_type": "tinyllava", | |
| "num_queries": 128, | |
| "num_resampler_layers": 3, | |
| "pad_token": "<|endoftext|>", | |
| "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" | |
| }, | |
| "resampler_hidden_size": 768, | |
| "text_config": { | |
| "_name_or_path": "microsoft/phi-2", | |
| "architectures": [ | |
| "PhiForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig", | |
| "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM" | |
| }, | |
| "bos_token_id": 50256, | |
| "embd_pdrop": 0.0, | |
| "eos_token_id": 50256, | |
| "hidden_act": "gelu_new", | |
| "hidden_size": 2560, | |
| "intermediate_size": 10240, | |
| "layer_norm_eps": 1e-05, | |
| "model_type": "phi", | |
| "num_hidden_layers": 32, | |
| "partial_rotary_factor": 0.4, | |
| "qk_layernorm": false, | |
| "resid_pdrop": 0.1, | |
| "torch_dtype": "float16", | |
| "vocab_size": 51200 | |
| }, | |
| "tokenizer_model_max_length": 3072, | |
| "tokenizer_name_or_path": "microsoft/phi-2", | |
| "tokenizer_padding_side": "right", | |
| "tokenizer_use_fast": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.42.4", | |
| "tune_type_connector": "full", | |
| "tune_type_llm": "full", | |
| "tune_type_vision_tower": "frozen", | |
| "tune_vision_tower_from_layer": 0, | |
| "use_cache": true, | |
| "vision_config": { | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "image_size": 384, | |
| "intermediate_size": 4304, | |
| "layer_norm_eps": 1e-06, | |
| "model_name_or_path": "google/siglip-so400m-patch14-384", | |
| "model_name_or_path2": "", | |
| "model_type": "siglip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 27, | |
| "patch_size": 14 | |
| }, | |
| "vision_feature_layer": -2, | |
| "vision_feature_select_strategy": "patch", | |
| "vision_hidden_size": 1152, | |
| "vision_model_name_or_path": "google/siglip-so400m-patch14-384", | |
| "vision_model_name_or_path2": "", | |
| "vocab_size": 51200 | |
| } | |