Phi-3.5-MoE-instruct / config.json
garg-amit's picture
upload model card
46fb142
{
"_name_or_path": "Phi-3.5-MoE-instruct",
"architectures": [
"PhiMoEForCausalLM"
],
"attention_bias": true,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_phimoe.PhiMoEConfig",
"AutoModelForCausalLM": "modeling_phimoe.PhiMoEForCausalLM"
},
"bos_token_id": 1,
"eos_token_id": 32000,
"hidden_act": "silu",
"hidden_dropout": 0.0,
"hidden_size": 4096,
"initializer_range": 0.02,
"input_jitter_noise": 0.01,
"intermediate_size": 6400,
"lm_head_bias": true,
"max_position_embeddings": 131072,
"model_type": "phimoe",
"num_attention_heads": 32,
"num_experts_per_tok": 2,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"num_local_experts": 16,
"original_max_position_embeddings": 4096,
"output_router_logits": false,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"long_factor": [
1.0199999809265137,
1.0299999713897705,
1.0399999618530273,
1.0499999523162842,
1.0499999523162842,
1.0499999523162842,
1.059999942779541,
1.059999942779541,
1.059999942779541,
1.059999942779541,
1.059999942779541,
1.059999942779541,
1.0999999046325684,
1.1799999475479126,
1.1799999475479126,
1.3700000047683716,
1.4899998903274536,
2.109999895095825,
2.8899998664855957,
3.9499998092651367,
4.299999713897705,
6.429999828338623,
8.09000015258789,
10.690000534057617,
12.050000190734863,
18.229999542236328,
18.84000015258789,
19.899999618530273,
21.420000076293945,
26.200000762939453,
34.28000259399414,
34.590003967285156,
38.730003356933594,
40.22000503540039,
42.54000473022461,
44.000003814697266,
47.590003967285156,
54.750003814697266,
56.19000244140625,
57.44000244140625,
57.4900016784668,
61.20000076293945,
61.540000915527344,
61.75,
61.779998779296875,
62.06999969482422,
63.11000061035156,
63.43000030517578,
63.560001373291016,
63.71000289916992,
63.92000198364258,
63.94000244140625,
63.94000244140625,
63.96000289916992,
63.980003356933594,
64.0300064086914,
64.0300064086914,
64.0300064086914,
64.04000854492188,
64.10000610351562,
64.19000244140625,
64.20999908447266,
64.75,
64.95999908447266
],
"long_mscale": 1.243163121016122,
"original_max_position_embeddings": 4096,
"short_factor": [
1.0,
1.0399999618530273,
1.0399999618530273,
1.0399999618530273,
1.0499999523162842,
1.0499999523162842,
1.0499999523162842,
1.0499999523162842,
1.0499999523162842,
1.0499999523162842,
1.0499999523162842,
1.0499999523162842,
1.0499999523162842,
1.0499999523162842,
1.059999942779541,
1.059999942779541,
1.0699999332427979,
1.0699999332427979,
1.0699999332427979,
1.0699999332427979,
1.1399999856948853,
1.159999966621399,
1.159999966621399,
1.159999966621399,
1.159999966621399,
1.1799999475479126,
1.1999999284744263,
1.3199999332427979,
1.3399999141693115,
1.3499999046325684,
1.3999998569488525,
1.4799998998641968,
1.4999998807907104,
1.589999794960022,
1.6499998569488525,
1.71999990940094,
1.8999998569488525,
1.9099998474121094,
1.9099998474121094,
1.9899998903274536,
1.9999998807907104,
1.9999998807907104,
2.009999990463257,
2.009999990463257,
2.009999990463257,
2.009999990463257,
2.009999990463257,
2.009999990463257,
2.009999990463257,
2.009999990463257,
2.009999990463257,
2.009999990463257,
2.009999990463257,
2.009999990463257,
2.009999990463257,
2.009999990463257,
2.009999990463257,
2.009999990463257,
2.009999990463257,
2.0999999046325684,
2.319999933242798,
2.419999837875366,
2.5899999141693115,
2.7899999618530273
],
"short_mscale": 1.243163121016122,
"type": "longrope"
},
"rope_theta": 10000.0,
"router_aux_loss_coef": 0.0,
"router_jitter_noise": 0.01,
"sliding_window": 131072,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.43.3",
"use_cache": true,
"vocab_size": 32064
}