38 lines
930 B
JSON
38 lines
930 B
JSON
|
{
|
||
|
|
"_name_or_path": "/raid/s3/opengptx/models/7B_EU24_4T_fw_iter_0238500_honey_2024_08_14_ckp-1350/checkpoint-1350",
|
||
|
|
"architectures": [
|
||
|
|
"LlamaForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_bias": false,
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"auto_map": {
|
||
|
|
"AutoTokenizer": [
|
||
|
|
"gptx_tokenizer.SPTokenizer",
|
||
|
|
null
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"bos_token_id": 1,
|
||
|
|
"eos_token_id": 2,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 4096,
|
||
|
|
"initializer_range": 0.0158,
|
||
|
|
"intermediate_size": 13440,
|
||
|
|
"max_position_embeddings": 4096,
|
||
|
|
"mlp_bias": false,
|
||
|
|
"model_type": "llama",
|
||
|
|
"num_attention_heads": 32,
|
||
|
|
"num_hidden_layers": 32,
|
||
|
|
"num_key_value_heads": 2,
|
||
|
|
"pad_token_id": 3,
|
||
|
|
"pretraining_tp": 1,
|
||
|
|
"rms_norm_eps": 1e-05,
|
||
|
|
"rope_scaling": null,
|
||
|
|
"rope_theta": 10000.0,
|
||
|
|
"tie_word_embeddings": true,
|
||
|
|
"tokenizer_class": "SPTokenizer",
|
||
|
|
"torch_dtype": "bfloat16",
|
||
|
|
"transformers_version": "4.43.2",
|
||
|
|
"use_cache": true,
|
||
|
|
"vocab_size": 250680
|
||
|
|
}
|