nm-testing/kv_cache_gptq_tinyllama-e2e

1{2  "architectures": [3    "LlamaForCausalLM"4  ],5  "attention_bias": false,6  "bos_token_id": 1,7  "eos_token_id": 2,8  "hidden_act": "silu",9  "hidden_size": 2048,10  "initializer_range": 0.02,11  "intermediate_size": 5632,12  "max_position_embeddings": 2048,13  "model_type": "llama",14  "num_attention_heads": 32,15  "num_hidden_layers": 22,16  "num_key_value_heads": 4,17  "pretraining_tp": 1,18  "quantization_config": {19    "config_groups": {20      "group_0": {21        "format": "pack-quantized",22        "input_activations": null,23        "output_activations": null,24        "targets": [25          "Linear"26        ],27        "weights": {28          "actorder": null,29          "block_structure": null,30          "dynamic": false,31          "group_size": null,32          "num_bits": 4,33          "observer": "memoryless_minmax",34          "observer_kwargs": {},35          "scale_dtype": null,36          "strategy": "channel",37          "symmetric": true,38          "type": "int",39          "zp_dtype": null40        }41      }42    },43    "format": "pack-quantized",44    "global_compression_ratio": null,45    "ignore": [46      "lm_head"47    ],48    "kv_cache_scheme": {49      "actorder": null,50      "block_structure": null,51      "dynamic": false,52      "group_size": null,53      "num_bits": 8,54      "observer": null,55      "observer_kwargs": {},56      "scale_dtype": null,57      "strategy": "tensor",58      "symmetric": true,59      "type": "float",60      "zp_dtype": null61    },62    "quant_method": "compressed-tensors",63    "quantization_status": "compressed",64    "sparsity_config": {},65    "transform_config": {},66    "version": "0.19.1a20260919"67  },68  "rms_norm_eps": 1e-05,69  "rope_scaling": null,70  "rope_theta": 10000.0,71  "tie_word_embeddings": false,72  "torch_dtype": "bfloat16",73  "transformers_version": "4.35.0",74  "use_cache": true,75  "vocab_size": 3200076}