{ "_name_or_path": "/home/lenovo/.cache/huggingface/hub/models--google--gemma-2-27b-it/snapshots/aaf20e6b9f4c0fcf043f6fb2a2068419086d77b0", "architectures": [ "Gemma2ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "attn_logit_softcapping": 50.0, "bos_token_id": 2, "cache_implementation": "hybrid", "compression_config": { "config_groups": { "group_0": { "input_activations": { "actorder": null, "block_structure": null, "dynamic": true, "group_size": null, "num_bits": 8, "observer": "memoryless", "observer_kwargs": {}, "strategy": "token", "symmetric": true, "type": "float" }, "output_activations": null, "targets": [ "Linear" ], "weights": { "actorder": null, "block_structure": null, "dynamic": false, "group_size": null, "num_bits": 8, "observer": "minmax", "observer_kwargs": {}, "strategy": "channel", "symmetric": true, "type": "float" } } }, "format": "float-quantized", "global_compression_ratio": 1.2112672088652379, "ignore": [ "lm_head" ], "kv_cache_scheme": null, "quant_method": "compressed-tensors", "quantization_status": "compressed" }, "eos_token_id": 1, "final_logit_softcapping": 30.0, "head_dim": 128, "hidden_act": "gelu_pytorch_tanh", "hidden_activation": "gelu_pytorch_tanh", "hidden_size": 4608, "initializer_range": 0.02, "intermediate_size": 36864, "max_position_embeddings": 8192, "model_type": "gemma2", "num_attention_heads": 32, "num_hidden_layers": 46, "num_key_value_heads": 16, "pad_token_id": 0, "query_pre_attn_scalar": 144, "rms_norm_eps": 1e-06, "rope_theta": 10000.0, "sliding_window": 4096, "sliding_window_size": 4096, "torch_dtype": "bfloat16", "transformers_version": "4.46.2", "use_cache": true, "vocab_size": 256000 }