File size: 1,729 Bytes
20e578a | 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 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 | {
"N": 20,
"base_config_dict": {
"_name_or_path": "TinyLlama/TinyLlama_v1.1",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"chunk_size_feed_forward": 0,
"dtype": "float32",
"eos_token_id": 2,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 2048,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"intermediate_size": 5632,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"max_position_embeddings": 2048,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 22,
"num_key_value_heads": 4,
"output_attentions": false,
"output_hidden_states": false,
"pad_token_id": null,
"pretraining_tp": 1,
"problem_type": null,
"return_dict": true,
"rms_norm_eps": 1e-05,
"rope_parameters": {
"rope_theta": 10000.0,
"rope_type": "default"
},
"tie_word_embeddings": false,
"transformers_version": "5.3.0",
"use_cache": true,
"vocab_size": 32000
},
"base_model_name_or_path": "TinyLlama/TinyLlama_v1.1",
"convergence_epsilon": 0.01,
"decoder_layer_indices": [
21
],
"encoder_layer_indices": [
0
],
"halting_strategy": "threshold",
"hidden_size": 2048,
"model_type": "lds",
"q_eval_interval": 1,
"q_threshold": 0.9,
"reasoning_layer_indices": [
1,
2,
3,
4,
5,
6,
7,
8,
9,
10,
11,
12,
13,
14,
15,
16,
17,
18,
19,
20
],
"transformers_version": "5.3.0",
"vocab_size": 32000
}
|