g8a9's picture
Upload LlamaForCausalLM
78480f0 verified
raw
history blame
886 Bytes
{
"_name_or_path": "bkp_rita/llama3-tweety-8b-italian-sft-uf_ita-merged/",
"additional_special_tokens_ids": [],
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"cls_token_id": null,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"mask_token_id": null,
"max_position_embeddings": 8192,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pad_token_id": 2,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 500000.0,
"tie_word_embeddings": false,
"tokenizer_class": "LlamaTokenizerFast",
"torch_dtype": "bfloat16",
"transformers_version": "4.37.2",
"unk_token_id": 0,
"use_cache": true,
"vocab_size": 32000
}