Qwen2-Math-RM-72B / config.json
clonefy's picture
Upload folder using huggingface_hub
46df1cb verified
raw
history blame contribute delete
819 Bytes
{
"architectures": [
"Qwen2ForRewardModel"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_qwen2_rm.Qwen2RMConfig",
"AutoModel": "modeling_qwen2_rm.Qwen2ForRewardModel"
},
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 8192,
"initializer_range": 0.02,
"intermediate_size": 29568,
"max_position_embeddings": 4096,
"max_window_layers": 70,
"model_type": "qwen2",
"num_attention_heads": 64,
"num_hidden_layers": 80,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-06,
"rope_theta": 10000.0,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.37.0",
"use_cache": true,
"use_mrope": false,
"use_sliding_window": false,
"vocab_size": 152064
}