rm_70b_soup / config.json
jdchang's picture
Upload model
4caa505 verified
{
"_name_or_path": "./models/m1",
"architectures": [
"AutoModelForCausalLMWithRM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "hf_utils.RewardModelConfig",
"AutoModel": "hf_utils.AutoModelForCausalLMWithRM"
},
"base_config": {
"_name_or_path": "meta-llama/Meta-Llama-3.1-70B-Instruct",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 128000,
"eos_token_id": [
128001,
128008,
128009
],
"hidden_size": 8192,
"intermediate_size": 28672,
"max_position_embeddings": 131072,
"model_type": "llama",
"num_attention_heads": 64,
"num_hidden_layers": 80,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 8.0,
"high_freq_factor": 4.0,
"low_freq_factor": 1.0,
"original_max_position_embeddings": 8192,
"rope_type": "llama3"
},
"rope_theta": 500000.0,
"torch_dtype": "bfloat16",
"use_cache": false,
"vocab_size": 128257
},
"base_model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
"bias": 0.0,
"bos_token_id": 128000,
"eos_token_id": [
128001,
128008,
128009
],
"hidden_act": "silu",
"hidden_size": 8192,
"initializer_range": 0.02,
"intermediate_size": 28672,
"max_position_embeddings": 131072,
"mlp_bias": false,
"model_type": "pairwise_rm",
"n_labels": 1,
"num_attention_heads": 64,
"num_hidden_layers": 80,
"num_key_value_heads": 8,
"p_dropout": 0.0,
"pretrain_cfg": {
"attn_implementation": "flash_attention_2",
"load_in_8bit": false,
"token": true,
"trust_remote_code": true
},
"pretrained": false,
"pretraining_tp": 1,
"return_logits": false,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 8.0,
"high_freq_factor": 4.0,
"low_freq_factor": 1.0,
"original_max_position_embeddings": 8192,
"rope_type": "llama3"
},
"rope_theta": 500000.0,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.46.1",
"use_cache": false,
"vocab_size": 128257
}