31 lines
761 B
JSON
31 lines
761 B
JSON
{
|
|
"_name_or_path": "/leonardo_scratch/large/userexternal/phuguetc/Minerva-7B-cpt-v1.0-mixed_recipe7-3epochs-safety-handcraft",
|
|
"architectures": [
|
|
"MistralForCausalLM"
|
|
],
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 1,
|
|
"eos_token_id": [
|
|
2,
|
|
51202
|
|
],
|
|
"head_dim": 128,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 4096,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 14336,
|
|
"max_position_embeddings": 4096,
|
|
"model_type": "mistral",
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 32,
|
|
"num_key_value_heads": 8,
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_theta": 10000.0,
|
|
"sliding_window": null,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.46.2",
|
|
"use_cache": false,
|
|
"vocab_size": 51264
|
|
}
|