File size: 1,345 Bytes
3443576 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 |
{
"_name_or_path": "meta-llama/Llama-2-7b-hf",
"architectures": [
"SparseLlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "ugly_utils.SparseLlamaConfig",
"AutoModelForCausalLM": "ugly_utils.SparseLlamaForCausalLM"
},
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 4096,
"model_type": "sparse_llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"thresholds": [
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0
],
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.40.0.dev0",
"us_sparse_regularization": false,
"use_cache": false,
"use_graceful_regularization": false,
"use_relu": true,
"use_sparse_model": true,
"use_sparse_predictor": false,
"use_sparse_regularization": false,
"vocab_size": 32000
}
|