30 lines
744 B
JSON
30 lines
744 B
JSON
{
|
|
"_name_or_path": "/mbz/shared/fan.zhou/spt/hf/exp2/pt_llama_0_4b_redpj_25B_raw/25B",
|
|
"architectures": [
|
|
"LlamaForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 1,
|
|
"eos_token_id": 2,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 1280,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 2048,
|
|
"max_position_embeddings": 2048,
|
|
"mlp_bias": false,
|
|
"model_type": "llama",
|
|
"num_attention_heads": 16,
|
|
"num_hidden_layers": 24,
|
|
"num_key_value_heads": 1,
|
|
"pretraining_tp": 1,
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_scaling": null,
|
|
"rope_theta": 10000.0,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "float32",
|
|
"transformers_version": "4.39.1",
|
|
"use_cache": false,
|
|
"vocab_size": 32000
|
|
}
|