INC4AI's picture
Upload quantized model MiniCPM5-1B-AutoRound-NVFP4-RTN
248dc1e verified
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 0,
"dtype": "bfloat16",
"eos_token_id": [
1,
130073
],
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 1536,
"initializer_range": 0.02,
"intermediate_size": 4608,
"max_position_embeddings": 131072,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"pad_token_id": 1,
"pretraining_tp": 1,
"quantization_config": {
"act_bits": 4,
"act_data_type": "nv_fp4_with_static_gs",
"act_dynamic": true,
"act_group_size": 16,
"act_sym": true,
"autoround_version": "0.13.0",
"bits": 4,
"block_name_to_quantize": "model.layers",
"data_type": "nv_fp",
"enable_quanted_input": false,
"extra_config": {
".*self_attn.*": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.0.self_attn.k_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.0.self_attn.o_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.0.self_attn.q_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.0.self_attn.v_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.1.self_attn.k_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.1.self_attn.o_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.1.self_attn.q_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.1.self_attn.v_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.10.self_attn.k_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.10.self_attn.o_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.10.self_attn.q_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.10.self_attn.v_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.11.self_attn.k_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.11.self_attn.o_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.11.self_attn.q_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.11.self_attn.v_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.12.self_attn.k_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.12.self_attn.o_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.12.self_attn.q_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.12.self_attn.v_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.13.self_attn.k_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.13.self_attn.o_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.13.self_attn.q_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.13.self_attn.v_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.14.self_attn.k_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.14.self_attn.o_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.14.self_attn.q_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.14.self_attn.v_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.15.self_attn.k_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.15.self_attn.o_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.15.self_attn.q_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.15.self_attn.v_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.16.self_attn.k_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.16.self_attn.o_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.16.self_attn.q_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.16.self_attn.v_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.17.self_attn.k_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.17.self_attn.o_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.17.self_attn.q_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.17.self_attn.v_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.18.self_attn.k_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.18.self_attn.o_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.18.self_attn.q_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.18.self_attn.v_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.19.self_attn.k_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.19.self_attn.o_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.19.self_attn.q_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.19.self_attn.v_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.2.self_attn.k_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.2.self_attn.o_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.2.self_attn.q_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.2.self_attn.v_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.20.self_attn.k_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.20.self_attn.o_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.20.self_attn.q_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.20.self_attn.v_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.21.self_attn.k_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.21.self_attn.o_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.21.self_attn.q_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.21.self_attn.v_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.22.self_attn.k_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.22.self_attn.o_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.22.self_attn.q_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.22.self_attn.v_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.23.self_attn.k_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.23.self_attn.o_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.23.self_attn.q_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.23.self_attn.v_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.3.self_attn.k_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.3.self_attn.o_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.3.self_attn.q_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.3.self_attn.v_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.4.self_attn.k_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.4.self_attn.o_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.4.self_attn.q_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.4.self_attn.v_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.5.self_attn.k_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.5.self_attn.o_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.5.self_attn.q_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.5.self_attn.v_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.6.self_attn.k_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.6.self_attn.o_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.6.self_attn.q_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.6.self_attn.v_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.7.self_attn.k_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.7.self_attn.o_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.7.self_attn.q_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.7.self_attn.v_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.8.self_attn.k_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.8.self_attn.o_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.8.self_attn.q_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.8.self_attn.v_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.9.self_attn.k_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.9.self_attn.o_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.9.self_attn.q_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
},
"model.layers.9.self_attn.v_proj": {
"act_bits": 16,
"act_data_type": "float",
"bits": 16,
"data_type": "float"
}
},
"group_size": 16,
"iters": 0,
"low_gpu_mem_usage": true,
"packing_format": "auto_round:llm_compressor",
"quant_method": "auto-round",
"sym": true
},
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 5000000,
"rope_type": "default"
},
"tie_word_embeddings": false,
"transformers_version": "5.9.0",
"use_cache": true,
"vocab_size": 130560
}