File size: 931 Bytes
48ecf04 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 |
{
"_name_or_path": "nvidia/Minitron-8B-Base",
"architectures": [
"NemotronForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 2,
"eos_token_id": 3,
"head_dim": 128,
"hidden_act": "relu2",
"hidden_size": 4096,
"initializer_range": 0.0134,
"intermediate_size": 16384,
"max_position_embeddings": 4096,
"mlp_bias": false,
"model_type": "nemotron",
"norm_eps": 1e-05,
"num_attention_heads": 48,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"quantization_config": {
"activation_scheme": "static",
"ignored_layers": [
"lm_head"
],
"kv_cache_scheme": "static",
"quant_method": "fp8"
},
"rope_percent": 0.5,
"rope_percentage": 0.5,
"rope_scaling": null,
"rope_theta": 10000,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.43.0.dev0",
"use_cache": true,
"vocab_size": 256000
}
|