winglian's picture
epoch 0.4 before divergence of loss, safetensors
a713ab6
raw
history blame
503 Bytes
{
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 6656,
"initializer_range": 0.02,
"intermediate_size": 17920,
"max_sequence_length": 2048,
"model_type": "llama",
"num_attention_heads": 52,
"num_hidden_layers": 60,
"pad_token_id": 0,
"rms_norm_eps": 1e-06,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.28.0.dev0",
"use_cache": true,
"vocab_size": 32000
}