File size: 1,697 Bytes
fe20bfe 94eec71 fe20bfe |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 |
{
"_name_or_path": "./bge-reranker-v2-minicpm-layerwise",
"architectures": [
"LayerWiseMiniCPMForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_minicpm_reranker.LayerWiseMiniCPMConfig",
"AutoModel": "BAAI/bge-reranker-v2-minicpm-layerwise--modeling_minicpm_reranker.LayerWiseMiniCPMModel",
"AutoModelForCausalLM": "modeling_minicpm_reranker.LayerWiseMiniCPMForCausalLM"
},
"bos_token_id": 1,
"dim_model_base": 256,
"eos_token_id": 2,
"head_multi": true,
"head_type": "simple",
"hidden_act": "silu",
"hidden_size": 2304,
"initializer_range": 0.1,
"intermediate_size": 5760,
"max_position_embeddings": 2048,
"model_type": "minicpm",
"num_attention_heads": 36,
"num_hidden_layers": 40,
"num_key_value_heads": 36,
"pretraining_tp": 1,
"quantization_config": {
"batch_size": 1,
"bits": 4,
"block_name_to_quantize": null,
"cache_block_outputs": true,
"damp_percent": 0.1,
"dataset": "c4",
"desc_act": false,
"exllama_config": {
"version": 1
},
"group_size": 128,
"max_input_length": null,
"model_seqlen": null,
"module_name_preceding_first_block": null,
"modules_in_block_to_quantize": null,
"pad_token_id": null,
"quant_method": "gptq",
"sym": true,
"tokenizer": null,
"true_sequential": true,
"use_cuda_fp16": false,
"use_exllama": false
},
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"scale_depth": 1.4,
"scale_emb": 12,
"start_layer": 8,
"torch_dtype": "float16",
"transformers_version": "4.44.2",
"use_cache": false,
"vocab_size": 122753
}
|