Text Generation
Transformers
Safetensors
llama
text-generation-inference
Inference Endpoints
Viking-13B / config.json
jonabur
100B
6011515
raw
history blame
860 Bytes
{
"_name_or_path": "/scratch/project_462000319/general-tools/viking_v2_checkpoints/viking_v2_13B_iter_0024000_bfloat16",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 4096,
"max_sequence_length": 4096,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"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": "4.37.2",
"untie_embeddings_and_output_weights": true,
"use_cache": true,
"vocab_size": 131072
}