| { |
| "_name_or_path": "SiliangZ/RM_Mistral_sft_init_ultrafeedbck_lr_5e6", |
| "architectures": [ |
| "MistralForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "bos_token_id": 1, |
| "eos_token_id": 2, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "id2label": { |
| "0": "LABEL_0" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 14336, |
| "label2id": { |
| "LABEL_0": 0 |
| }, |
| "max_position_embeddings": 32768, |
| "model_type": "mistral", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 8, |
| "pad_token_id": 32000, |
| "rms_norm_eps": 1e-05, |
| "rope_theta": 10000.0, |
| "sliding_window": 4096, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.47.0", |
| "use_cache": false, |
| "vocab_size": 32001 |
| } |
|
|