mpasila's picture
Trained with Unsloth
bbcc46a verified
raw
history blame
837 Bytes
{
"_name_or_path": "mpasila/Viking-33B-1000B",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 7168,
"initializer_range": 0.02,
"intermediate_size": 20480,
"max_position_embeddings": 4096,
"max_sequence_length": 4096,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 56,
"num_hidden_layers": 56,
"num_key_value_heads": 8,
"pad_token_id": -1,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.41.1",
"unsloth_version": "2024.5",
"untie_embeddings_and_output_weights": true,
"use_cache": true,
"vocab_size": 131072
}