Safetensors
llama
orchid13's picture
initial commit
9df4d20
raw
history blame contribute delete
957 Bytes
{
"_name_or_path": "/shared/gojek/daryl_tmp/cpt_hf/ba23842",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 128000,
"config_overrides": {
"torch_dtype": "bfloat16"
},
"eos_token_id": 128001,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 8192,
"mlp_bias": false,
"model_type": "llama",
"name": "hf_causal_lm",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pretrained": true,
"pretrained_model_name_or_path": "aisingapore/llama3-8b-cpt-sea-lionv2.1-instruct",
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 500000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.43.4",
"use_cache": true,
"use_flash_attention_2": true,
"vocab_size": 128256
}