Text Generation
Transformers
Safetensors
falcon
text-generation-inference
quantumaikr's picture
Upload FalconForCausalLM
3db30d1
raw
history blame contribute delete
614 Bytes
{
"_name_or_path": "falcon-180B-chat-instruct",
"alibi": false,
"architectures": [
"FalconForCausalLM"
],
"attention_dropout": 0.0,
"bias": false,
"bos_token_id": 11,
"eos_token_id": 11,
"hidden_dropout": 0.0,
"hidden_size": 14848,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "falcon",
"multi_query": true,
"new_decoder_architecture": true,
"num_attention_heads": 232,
"num_hidden_layers": 80,
"num_kv_heads": 8,
"parallel_attn": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.31.0",
"use_cache": true,
"vocab_size": 65024
}