OA_falcon_33b / config.json
Ontocord.AI
Upload RWForCausalLM
dc8d3dd
raw
history blame
1.26 kB
{
"_name_or_path": "OpenAssistant/falcon-40b-sft-top1-560",
"alibi": false,
"apply_residual_connection_post_layernorm": false,
"architectures": [
"RWForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "OpenAssistant/falcon-40b-sft-top1-560--configuration_RW.RWConfig",
"AutoModel": "OpenAssistant/falcon-40b-sft-top1-560--modelling_RW.RWModel",
"AutoModelForCausalLM": "OpenAssistant/falcon-40b-sft-top1-560--modelling_RW.RWForCausalLM",
"AutoModelForQuestionAnswering": "OpenAssistant/falcon-40b-sft-top1-560--modelling_RW.RWForQuestionAnswering",
"AutoModelForSequenceClassification": "OpenAssistant/falcon-40b-sft-top1-560--modelling_RW.RWForSequenceClassification",
"AutoModelForTokenClassification": "OpenAssistant/falcon-40b-sft-top1-560--modelling_RW.RWForTokenClassification"
},
"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,
"max_seq_len": 65536,
"model_type": "RefinedWeb",
"n_head": 128,
"n_head_kv": 8,
"n_layer": 60,
"parallel_attn": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.30.1",
"use_cache": true,
"vocab_size": 65040
}