vxbrandon's picture
Training in progress, step 500
2a1e815 verified
{
"_name_or_path": "mistralai/Mistral-7B-v0.1",
"architectures": [
"SparseMistralforCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoModelForCausalLM": "ugly_utils.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_llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"sliding_window": 4096,
"thresholds": [
0.01905716396868229,
0.027081236243247986,
0.04513540118932724,
0.05315947160124779,
0.06720159947872162,
0.07923770695924759,
0.08726178109645844,
0.09528584778308868,
0.10130390524864197,
0.0992978885769844,
0.10732196271419525,
0.10732196271419525,
0.11735205352306366,
0.11735205352306366,
0.12738214433193207,
0.14343027770519257,
0.16349045932292938,
0.17552657425403595,
0.19157472252845764,
0.20762285590171814,
0.21364091336727142,
0.22968906164169312,
0.22768303751945496,
0.2357071191072464,
0.23971915245056152,
0.23971915245056152,
0.2357071191072464,
0.23771312832832336,
0.2357071191072464,
0.23370109498500824,
0.23971915245056152,
0.24774321913719177
],
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.36.2",
"us_sparse_regularization": false,
"use_cache": false,
"use_graceful_regularization": false,
"use_relu": false,
"use_sparse_model": true,
"use_sparse_predictor": false,
"use_sparse_regularization": false,
"vocab_size": 32000
}