|
{ |
|
"_attn_implementation_autoset": true, |
|
"_name_or_path": "C:\\Users\\sdp\\Downloads\\phi-4-draft-120m-fw_10bt-cp-fw_5bt-stckv2_10bt-ft\\phi-4-draft", |
|
"architectures": [ |
|
"Phi3ForCausalLM" |
|
], |
|
"attention_bias": false, |
|
"attention_dropout": 0.0, |
|
"auto_map": { |
|
"AutoConfig": "configuration_phi3.Phi3Config", |
|
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM", |
|
"AutoTokenizer": "Xenova/gpt-4o" |
|
}, |
|
"bos_token_id": 199999, |
|
"embd_pdrop": 0.0, |
|
"eos_token_id": 199999, |
|
"full_attn_mod": 1, |
|
"hidden_act": "silu", |
|
"hidden_size": 512, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 1408, |
|
"interpolate_factor": 1, |
|
"lm_head_bias": false, |
|
"max_position_embeddings": 4096, |
|
"mlp_bias": false, |
|
"model_type": "phi3", |
|
"num_attention_heads": 8, |
|
"num_hidden_layers": 6, |
|
"num_key_value_heads": 8, |
|
"original_max_position_embeddings": 4096, |
|
"pad_token_id": 199999, |
|
"partial_rotary_factor": 0.75, |
|
"resid_pdrop": 0.0, |
|
"rms_norm_eps": 1e-05, |
|
"rope_scaling": null, |
|
"rope_theta": 10000.0, |
|
"sliding_window": 262144, |
|
"tie_word_embeddings": true, |
|
"transformers_version": "4.49.0", |
|
"use_cache": true, |
|
"vocab_size": 200064 |
|
} |