DippyAI/reference_model
07
1{2 "_name_or_path": "lemon07r/Gemma-2-Ataraxy-v4c-9B",3 "architectures": [4 "Gemma2ForCausalLM"5 ],6 "attention_bias": false,7 "attention_dropout": 0.0,8 "attn_logit_softcapping": 50.0,9 "bos_token_id": 2,10 "cache_implementation": "hybrid",11 "eos_token_id": 1,12 "final_logit_softcapping": 30.0,13 "head_dim": 256,14 "hidden_act": "gelu_pytorch_tanh",15 "hidden_activation": "gelu_pytorch_tanh",16 "hidden_size": 3584,17 "initializer_range": 0.02,18 "intermediate_size": 14336,19 "max_position_embeddings": 8192,20 "model_type": "gemma2",21 "num_attention_heads": 16,22 "num_hidden_layers": 42,23 "num_key_value_heads": 8,24 "pad_token_id": 0,25 "query_pre_attn_scalar": 224,26 "rms_norm_eps": 1e-06,27 "rope_theta": 10000.0,28 "sliding_window": 4096,29 "sliding_window_size": 4096,30 "torch_dtype": "bfloat16",31 "transformers_version": "4.43.3",32 "use_cache": true,33 "vocab_size": 25600034}35 