File size: 1,607 Bytes
1598a73 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 |
{
"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-3-8B-Instruct",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 128000,
"eos_token_id": 128009,
"hidden_size": 4096,
"intermediate_size": 14336,
"max_position_embeddings": 8192,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-05,
"rope_theta": 500000.0,
"torch_dtype": "bfloat16",
"use_cache": false,
"vocab_size": 128257
},
"base_model": "meta-llama/Meta-Llama-3-8B-Instruct",
"bias": 0.0,
"bos_token_id": 128000,
"eos_token_id": 128009,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 8192,
"mlp_bias": false,
"model_type": "pairwise_rm",
"n_labels": 1,
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"p_dropout": 0.0,
"pretrain_cfg": {
"load_in_8bit": false,
"token": true,
"trust_remote_code": null
},
"pretrained": true,
"pretraining_tp": 1,
"return_logits": false,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 500000.0,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.43.4",
"use_cache": false,
"vocab_size": 128257
}
|