Mistral_Sparse / config.json
vxbrandon's picture
End of training
b5aa62d verified
raw
history blame contribute delete
No virus
915 Bytes
{
"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": 64,
"initializer_range": 0.02,
"intermediate_size": 64,
"max_position_embeddings": 131072,
"model_type": "sparse_mistral",
"num_attention_heads": 32,
"num_hidden_layers": 4,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-06,
"rope_theta": 10000.0,
"sliding_window": 4096,
"thresholds": [
0.0,
0.0,
0.0,
0.0
],
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.36.2",
"use_cache": true,
"use_sparse_model": true,
"use_sparse_predictor": false,
"use_sparse_regularization": false,
"vocab_size": 32000
}