Transformers
Safetensors
English
deberta-v2
reward_model
reward-model
RLHF
evaluation
llm
instruction
reranking
Inference Endpoints
Better-PairRM / config.json
maywell's picture
Upload folder using huggingface_hub
e50d81e verified
raw history blame
No virus
967 Bytes
{
"architectures": [
"DebertaV2PairRM"
],
"attention_probs_dropout_prob": 0.1,
"cand1_prefix_id": 128002,
"cand2_prefix_id": 128003,
"cand_prefix_id": 128004,
"drop_out": 0.05,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 4096,
"layer_norm_eps": 1e-07,
"max_position_embeddings": 512,
"max_relative_positions": -1,
"model_type": "deberta-v2",
"n_tasks": 1,
"norm_rel_ebd": "layer_norm",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"pad_token_id": 0,
"pooler_dropout": 0,
"pooler_hidden_act": "gelu",
"pooler_hidden_size": 1024,
"pos_att_type": [
"p2c",
"c2p"
],
"position_biased_input": false,
"position_buckets": 256,
"relative_attention": true,
"share_att_key": true,
"source_prefix_id": 128001,
"torch_dtype": "float32",
"transformers_version": "4.37.0",
"type_vocab_size": 0,
"vocab_size": 128005
}