ce-lery's picture
feat: pretrained by recipe v0.1.0
c783850
{
"_name_or_path": "None",
"architectures": [
"MistralForCausalLM"
],
"bos_token_id": 0,
"eos_token_id": 0,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 2400,
"max_position_embeddings": 4096,
"model_type": "mistral",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-05,
"rope_theta": 10000.0,
"sliding_window": 1024,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.35.2",
"use_cache": true,
"vocab_size": 50257
}