test-22B / config.json
Devio's picture
Upload LlamaForCausalLM
e3889fc
{
"_name_or_path": "/mnt/share/master31/20B_v2_adam_iter-000100-ckpt.pth/",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 6656,
"initializer_range": 0.02,
"intermediate_size": 17920,
"max_position_embeddings": 2048,
"max_sequence_length": 2048,
"model_type": "llama",
"num_attention_heads": 52,
"num_hidden_layers": 40,
"num_key_value_heads": 52,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.30.2",
"use_cache": true,
"vocab_size": 32000
}