| { | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_llama.LlamaConfig", | |
| "AutoModelForCausalLM": "modeling_llama.LlamaForCausalLM" | |
| }, | |
| "bos_token_id": 128000, | |
| "cache_window_ratio": 0.25, | |
| "cache_window_size": 768, | |
| "eos_token_id": 128009, | |
| "fastlora_n_global_tokens": 64, | |
| "fastlora_r": 32, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 3072, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "max_position_embeddings": 131072, | |
| "mlp_bias": false, | |
| "model_type": "llama_adapter", | |
| "n_sink_tokens": 10, | |
| "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": { | |
| "factor": 32.0, | |
| "high_freq_factor": 4.0, | |
| "low_freq_factor": 1.0, | |
| "original_max_position_embeddings": 8192, | |
| "rope_type": "llama3" | |
| }, | |
| "rope_theta": 500000.0, | |
| "scale_factor": 2.0, | |
| "sliding_window": false, | |
| "think_factor": 1.25, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "training_scale_factor": 2.0, | |
| "transformers_version": "4.53.0", | |
| "unsloth_fixed": true, | |
| "unsloth_version": "2025.2.4", | |
| "use_cache": true, | |
| "use_global_tokens": true, | |
| "vocab_size": 128256 | |
| } | |