minicpm-v2_6 / config.json
sabre-code's picture
Pushing loaded in 4bit to hub
fc15a1f verified
{
"_name_or_path": "openbmb/MiniCPM-V-2_6",
"architectures": [
"MiniCPMV"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "openbmb/MiniCPM-V-2_6--configuration_minicpm.MiniCPMVConfig",
"AutoModel": "openbmb/MiniCPM-V-2_6--modeling_minicpmv.MiniCPMV",
"AutoModelForCausalLM": "openbmb/MiniCPM-V-2_6--modeling_minicpmv.MiniCPMV"
},
"batch_vision_input": true,
"bos_token_id": 151643,
"drop_vision_last_layer": false,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_size": 448,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 32768,
"max_window_layers": 28,
"model_type": "minicpmv",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"patch_size": 14,
"quantization_config": {
"_load_in_4bit": true,
"_load_in_8bit": false,
"bnb_4bit_compute_dtype": "float32",
"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": null,
"llm_int8_threshold": 6.0,
"load_in_4bit": true,
"load_in_8bit": false,
"quant_method": "bitsandbytes"
},
"query_num": 64,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"slice_config": {
"max_slice_nums": 9,
"model_type": "minicpmv"
},
"slice_mode": true,
"sliding_window": 131072,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.42.4",
"use_cache": true,
"use_image_id": true,
"use_sliding_window": false,
"version": 2.6,
"vision_batch_size": 16,
"vision_config": {
"hidden_size": 1152,
"image_size": 980,
"intermediate_size": 4304,
"model_type": "siglip_vision_model",
"num_attention_heads": 16,
"num_hidden_layers": 27,
"patch_size": 14
},
"vocab_size": 151666
}