Text Generation
Transformers
PyTorch
RefinedWeb
falcon-40b
rlhf
falcon
custom_code
text-generation-inference
Inference Endpoints
alfred-40b-0723 / config.json
ohallstrom's picture
Upload RWForCausalLM
6ee1b99
raw
history blame
702 Bytes
{
"alibi": false,
"apply_residual_connection_post_layernorm": false,
"architectures": [
"RWForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_RW.RWConfig",
"AutoModelForCausalLM": "modeling_RW.RWForCausalLM"
},
"bias": false,
"bos_token_id": 11,
"eos_token_id": 11,
"hidden_dropout": 0.0,
"hidden_size": 8192,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "RefinedWeb",
"multi_query": true,
"n_head": 128,
"n_head_kv": 8,
"n_layer": 60,
"parallel_attn": true,
"single_ln": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.31.0",
"use_cache": true,
"vocab_size": 65024
}