nzora-ap-550m-id-dev2 / config.json
nqzfaizal77ai's picture
Upload model trained with transformers trainer on nqzfaizal77ai/leipzig_id_mixed_tufs4_2012_sentences,cw 128,lr 1e-4,2 epoch,batch size 4,cosine with restart
0cad172 verified
{
"_name_or_path": "phi3.5-550m-id-dev",
"architectures": [
"Phi3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "nqzfaizal77ai/phi-3.5-550m-pruned--configuration_phi3.Phi3Config",
"AutoModelForCausalLM": "nqzfaizal77ai/phi-3.5-550m-pruned--modeling_phi3.Phi3ForCausalLM"
},
"bos_token_id": 1,
"embd_pdrop": 0.0,
"eos_token_id": 32000,
"hidden_act": "silu",
"hidden_size": 1440,
"initializer_range": 0.02,
"intermediate_size": 5760,
"max_position_embeddings": 4096,
"model_type": "phi3",
"num_attention_heads": 10,
"num_hidden_layers": 14,
"num_key_value_heads": 10,
"original_max_position_embeddings": 4096,
"pad_token_id": 32000,
"resid_pdrop": 0.0,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"long_factor": [
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0
],
"short_factor": [
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0
],
"type": "longrope"
},
"rope_theta": 10000.0,
"sliding_window": 262144,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.45.1",
"use_cache": true,
"vocab_size": 32064
}