Text Generation
Transformers
Safetensors
6 languages
llama
Eval Results
Inference Endpoints
text-generation-inference
Orca-2-13b-SFT-v6 / config.json
Locutusque's picture
Upload LlamaForCausalLM
f2b12e0
{
"_name_or_path": "Locutusque/Orca-2-13b-SFT-v6",
"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,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.36.2",
"use_cache": true,
"vocab_size": 32003
}