{ | |
"_name_or_path": "/media/mla100scus/Projects_1/Code-290k-13B", | |
"architectures": [ | |
"LlamaForCausalLM" | |
], | |
"bos_token_id": 1, | |
"eos_token_id": 2, | |
"hidden_act": "silu", | |
"hidden_size": 5120, | |
"initializer_range": 0.02, | |
"intermediate_size": 13824, | |
"max_position_embeddings": 4096, | |
"model_type": "llama", | |
"num_attention_heads": 40, | |
"num_hidden_layers": 40, | |
"num_key_value_heads": 40, | |
"pad_token_id": 0, | |
"pretraining_tp": 1, | |
"rms_norm_eps": 1e-05, | |
"rope_scaling": null, | |
"tie_word_embeddings": false, | |
"torch_dtype": "bfloat16", | |
"transformers_version": "4.28.1", | |
"use_cache": false, | |
"vocab_size": 32000 | |
} | |