lukeleeai's picture
End of training
dd481c5 verified
raw
history blame contribute delete
No virus
1.81 kB
{
"_name_or_path": "mistralai/Mistral-7B-v0.1",
"architectures": [
"SparseMistralforCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "sparsification_sftt.SparseMistralConfig",
"AutoModelForCausalLM": "sparsification_sftt.SparseMistralforCausalLM"
},
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 32768,
"model_type": "sparse_mistral",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-05,
"rope_theta": 10000.0,
"sliding_window": 4096,
"thresholds": [
0.0631895586848259,
0.07923770695924759,
0.089267797768116,
0.10732196271419525,
0.12738214433193207,
0.1414242684841156,
0.15546639263629913,
0.16349045932292938,
0.1675025075674057,
0.1675025075674057,
0.1675025075674057,
0.1735205501317978,
0.17552657425403595,
0.1775325983762741,
0.18956869840621948,
0.1935807317495346,
0.19759276509284973,
0.21364091336727142,
0.22367100417613983,
0.23169508576393127,
0.22367100417613983,
0.22968906164169312,
0.22367100417613983,
0.22367100417613983,
0.23169508576393127,
0.23971915245056152,
0.2457372099161148,
0.2577733099460602,
0.2678034007549286,
0.27382147312164307,
0.27582746744155884,
0.277833491563797
],
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.37.2",
"us_sparse_regularization": true,
"use_cache": true,
"use_graceful_regularization": true,
"use_relu": false,
"use_sparse_model": true,
"use_sparse_predictor": false,
"use_sparse_regularization": false,
"vocab_size": 32000
}