Text Generation
Transformers
Safetensors
llama
llama2
text-generation-inference
Inference Endpoints
Giraffe-13b-32k-v3 / config.json
arvindabacus's picture
Update config.json
bbc483f
raw
history blame
696 Bytes
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_length": 32768,
"max_position_embeddings": 32768,
"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": {
"factor": 8.0,
"type": "linear"
},
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.35.2",
"use_cache": false,
"vocab_size": 32000
}