|
{ |
|
"_name_or_path": "yeniceriSGK/miniCPM-pi-brain-v1", |
|
"architectures": [ |
|
"MiniCPMForCausalLM" |
|
], |
|
"attention_bias": false, |
|
"attention_dropout": 0.0, |
|
"auto_map": { |
|
"AutoConfig": "openbmb/MiniCPM-2B-sft-fp32--configuration_minicpm.MiniCPMConfig", |
|
"AutoModel": "openbmb/MiniCPM-2B-sft-fp32--modeling_minicpm.MiniCPMModel", |
|
"AutoModelForCausalLM": "openbmb/MiniCPM-2B-sft-fp32--modeling_minicpm.MiniCPMForCausalLM", |
|
"AutoModelForSeq2SeqLM": "openbmb/MiniCPM-2B-sft-fp32--modeling_minicpm.MiniCPMForCausalLM", |
|
"AutoModelForSequenceClassification": "openbmb/MiniCPM-2B-sft-fp32--modeling_minicpm.MiniCPMForSequenceClassification" |
|
}, |
|
"bos_token_id": 1, |
|
"dim_model_base": 256, |
|
"eos_token_id": 2, |
|
"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": [ |
|
"Maaz911/Mistral-Instruct-DataV1" |
|
], |
|
"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": true |
|
}, |
|
"rms_norm_eps": 1e-05, |
|
"rope_scaling": null, |
|
"rope_theta": 10000.0, |
|
"scale_depth": 1.4, |
|
"scale_emb": 12, |
|
"torch_dtype": "float16", |
|
"transformers_version": "4.37.2", |
|
"use_cache": true, |
|
"vocab_size": 122753 |
|
} |
|
|