26 lines
603 B
JSON
26 lines
603 B
JSON
{
|
|
"_name_or_path": "/workspace/llama-7b-hf",
|
|
"architectures": [
|
|
"LlamaForCausalLM"
|
|
],
|
|
"bos_token_id": 0,
|
|
"eos_token_id": 1,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 4096,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 11008,
|
|
"max_position_embeddings": 4096,
|
|
"max_seq_len": 4096,
|
|
"max_sequence_length": 4096,
|
|
"model_type": "llama",
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 32,
|
|
"pad_token_id": -1,
|
|
"rms_norm_eps": 1e-06,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "float32",
|
|
"transformers_version": "4.29.2",
|
|
"use_cache": false,
|
|
"vocab_size": 32000
|
|
}
|