|
{ |
|
"architectures": [ |
|
"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": 128, |
|
"intermediate_size": 14336, |
|
"max_position_embeddings": 8192, |
|
"model_type": "llama", |
|
"num_attention_heads": 32, |
|
"num_hidden_layers": 4, |
|
"num_key_value_heads": 8, |
|
"rms_norm_eps": 1e-05, |
|
"rope_theta": 500000.0, |
|
"torch_dtype": "bfloat16", |
|
"vocab_size": 128256 |
|
}, |
|
"base_model": "meta-llama/Meta-Llama-3-8B-Instruct", |
|
"bias": 0.0, |
|
"hidden_size": 128, |
|
"model_type": "pairwise_rm", |
|
"n_labels": 1, |
|
"p_dropout": 0.0, |
|
"pretrain_cfg": {}, |
|
"pretrained": false, |
|
"return_logits": false, |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.43.3", |
|
"vocab_size": 128256 |
|
} |
|
|