NextGLab/ORANSight_Gemma_2_2B_Instruct

1{2  "_name_or_path": "unsloth/gemma-2-2b-it-bnb-4bit",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": [12    1,13    10714  ],15  "final_logit_softcapping": 30.0,16  "head_dim": 256,17  "hidden_act": "gelu_pytorch_tanh",18  "hidden_activation": "gelu_pytorch_tanh",19  "hidden_size": 2304,20  "initializer_range": 0.02,21  "intermediate_size": 9216,22  "max_position_embeddings": 8192,23  "model_type": "gemma2",24  "num_attention_heads": 8,25  "num_hidden_layers": 26,26  "num_key_value_heads": 4,27  "pad_token_id": 0,28  "query_pre_attn_scalar": 256,29  "rms_norm_eps": 1e-06,30  "rope_scaling": null,31  "rope_theta": 10000.0,32  "sliding_window": 4096,33  "torch_dtype": "bfloat16",34  "transformers_version": "4.47.1",35  "unsloth_version": "2024.12.12",36  "use_cache": true,37  "vocab_size": 25600038}39