|
{ |
|
"_name_or_path": "openbmb/CPM-2B", |
|
"architectures": [ |
|
"MiniCPMForCausalLM" |
|
], |
|
"auto_map": { |
|
"AutoConfig": "configuration_minicpm.MiniCPMConfig", |
|
"AutoModel": "modeling_minicpm.MiniCPMModel", |
|
"AutoModelForCausalLM": "modeling_minicpm.MiniCPMForCausalLM", |
|
"AutoModelForSeq2SeqLM": "modeling_minicpm.MiniCPMForCausalLM", |
|
"AutoModelForSequenceClassification": "modeling_minicpm.MiniCPMForSequenceClassification" |
|
}, |
|
"bos_token_id": 1, |
|
"eos_token_id": [2,73440], |
|
"pad_token_id": 2, |
|
"hidden_act": "silu", |
|
"hidden_size": 4096, |
|
"initializer_range": 0.1, |
|
"intermediate_size": 16384, |
|
"max_position_embeddings": 32768, |
|
"model_type": "minicpm", |
|
"num_attention_heads": 32, |
|
"num_hidden_layers": 1, |
|
"num_key_value_heads": 2, |
|
"rms_norm_eps": 1e-06, |
|
"rope_scaling": { |
|
"rope_type": "longrope", |
|
"long_factor": [0.9977997200264581, 1.014658295992452, 1.0349680404997148, 1.059429246056193, 1.0888815016813513, 1.1243301355211495, 1.166977103606075, 1.2182568066927284, 1.2798772354275727, 1.3538666751582975, 1.4426259039919596, 1.5489853358570191, 1.6762658237220625, 1.8283407612492941, 2.0096956085876183, 2.225478927469756, 2.481536379650452, 2.784415934557119, 3.1413289096347365, 3.560047844772632, 4.048719380066383, 4.615569542115128, 5.2684819496549835, 6.014438591970396, 6.858830049237097, 7.804668263503327, 8.851768731513417, 9.99600492938444, 11.228766118181639, 12.536757560834843, 13.902257701387796, 15.303885189125953, 16.717837610115794, 18.119465097853947, 19.484965238406907, 20.792956681060105, 22.02571786985731, 23.16995406772833, 24.217054535738416, 25.16289275000465, 26.007284207271347, 26.753240849586767, 27.40615325712662, 27.973003419175363, 28.461674954469114, 28.880393889607006, 29.237306864684626, 29.540186419591297, 29.79624387177199, 30.01202719065413, 30.193382037992453, 30.34545697551969, 30.47273746338473, 30.579096895249787, 30.66785612408345, 30.741845563814174, 30.80346599254902, 30.85474569563567, 30.897392663720595, 30.932841297560394, 30.962293553185553, 30.986754758742034, 31.007064503249293, 31.02392307921529], |
|
"short_factor": [0.9977997200264581, 1.014658295992452, 1.0349680404997148, 1.059429246056193, 1.0888815016813513, 1.1243301355211495, 1.166977103606075, 1.2182568066927284, 1.2798772354275727, 1.3538666751582975, 1.4426259039919596, 1.5489853358570191, 1.6762658237220625, 1.8283407612492941, 2.0096956085876183, 2.225478927469756, 2.481536379650452, 2.784415934557119, 3.1413289096347365, 3.560047844772632, 4.048719380066383, 4.615569542115128, 5.2684819496549835, 6.014438591970396, 6.858830049237097, 7.804668263503327, 8.851768731513417, 9.99600492938444, 11.228766118181639, 12.536757560834843, 13.902257701387796, 15.303885189125953, 16.717837610115794, 18.119465097853947, 19.484965238406907, 20.792956681060105, 22.02571786985731, 23.16995406772833, 24.217054535738416, 25.16289275000465, 26.007284207271347, 26.753240849586767, 27.40615325712662, 27.973003419175363, 28.461674954469114, 28.880393889607006, 29.237306864684626, 29.540186419591297, 29.79624387177199, 30.01202719065413, 30.193382037992453, 30.34545697551969, 30.47273746338473, 30.579096895249787, 30.66785612408345, 30.741845563814174, 30.80346599254902, 30.85474569563567, 30.897392663720595, 30.932841297560394, 30.962293553185553, 30.986754758742034, 31.007064503249293, 31.02392307921529], |
|
"original_max_position_embeddings": 32768 |
|
}, |
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.36.0", |
|
"use_cache": true, |
|
"vocab_size": 73448, |
|
"scale_emb": 12, |
|
"dim_model_base": 256, |
|
"scale_depth": 1.4, |
|
"tie_word_embeddings": false, |
|
"bias": false, |
|
"head_dim": 128 |
|
} |
|
|