| {"architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 2048, "model_type": "llama", "num_attention_heads": 32, "num_hidden_layers": 1, "pad_token_id": 0, "rms_norm_eps": 1e-06, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.28.1", "use_cache": true, "vocab_size": 32000, "clover": {"num_heads": 5, "num_layers": 2, "heads_coefficient": 1.0, "decay_coefficient": 0.7}} |