nicholasKluge's picture
Training in progress, epoch 1
840b6c0
raw
history blame
870 Bytes
{
"_name_or_path": "nicholasKluge/Teeny-tiny-llama-162m",
"architectures": [
"LlamaForSequenceClassification"
],
"attention_bias": false,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 768,
"id2label": {
"0": "NEGATIVE",
"1": "POSITIVE"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"NEGATIVE": 0,
"POSITIVE": 1
},
"max_position_embeddings": 2048,
"model_type": "llama",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"num_key_value_heads": 12,
"pad_token_id": 3,
"pretraining_tp": 1,
"problem_type": "single_label_classification",
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.35.2",
"use_cache": false,
"vocab_size": 32000
}