| {"_name_or_path": "semran1/l3.2-3b-63-deg2", "architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "aux_loss_type": "mseloss", "bos_token_id": 128000, "check_data_cls_loss": false, "del_layers": [], "eos_token_id": 128009, "head_dim": 128, "hidden_act": "silu", "hidden_size": 1536, "initializer_range": 0.02, "intermediate_size": 8192, "kl_temperature": 10.0, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "num_attention_heads": 24, "num_hidden_layers": 28, "num_key_value_heads": 8, "pad_token_id": 128004, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "student_attn_from_scratch": false, "target_hidden_size": 1536, "target_rms_norm_eps": 1e-05, "tie_word_emb_proj": 1, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "transformers_version": "4.42.0", "unsloth_fixed": true, "use_additional_align": false, "use_all_attn": 1, "use_attn_map": false, "use_aux_loss": true, "use_cache": true, "use_in_out_mlp": false, "use_logits_loss": true, "use_ntp_loss": true, "use_std_like_attn": false, "vocab_size": 128256} |