| { |
| "architectures": [ |
| "AutoModelForCausalLMWithRM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "hf_utils.RewardModelConfig", |
| "AutoModel": "hf_utils.AutoModelForCausalLMWithRM" |
| }, |
| "base_config": { |
| "_name_or_path": "jdchang/llama3-small", |
| "architectures": [ |
| "LlamaForCausalLM" |
| ], |
| "bos_token_id": 128000, |
| "eos_token_id": 128009, |
| "hidden_size": 512, |
| "intermediate_size": 14336, |
| "max_position_embeddings": 8192, |
| "model_type": "llama", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 2, |
| "num_key_value_heads": 8, |
| "rms_norm_eps": 1e-05, |
| "rope_theta": 500000.0, |
| "torch_dtype": "float32", |
| "use_cache": false, |
| "vocab_size": 128257 |
| }, |
| "base_model": "jdchang/llama3-small", |
| "bias": 0.0, |
| "bos_token_id": 128000, |
| "eos_token_id": 128009, |
| "hidden_act": "silu", |
| "hidden_size": 512, |
| "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": 2, |
| "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 |
| } |
|
|
