26 lines
635 B
JSON
26 lines
635 B
JSON
{
|
|
"_name_or_path": "nvidia/Minitron-8B-Base",
|
|
"architectures": [
|
|
"NemotronForCausalLM"
|
|
],
|
|
"bos_token_id": 2,
|
|
"eos_token_id": 3,
|
|
"hidden_act": "relu2",
|
|
"hidden_size": 4096,
|
|
"initializer_range": 0.0134,
|
|
"intermediate_size": 16384,
|
|
"max_position_embeddings": 4096,
|
|
"model_type": "nemotron",
|
|
"num_attention_heads": 48,
|
|
"num_hidden_layers": 32,
|
|
"num_key_value_heads": 8,
|
|
"norm_eps": 1e-05,
|
|
"rope_theta": 10000,
|
|
"partial_rotary_factor": 0.5,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.44.0",
|
|
"use_cache": true,
|
|
"vocab_size": 256000,
|
|
"head_dim": 128
|
|
} |