nm-testing/tinyllama-one-shot-static-quant-test-compressed

1{2  "_name_or_path": "/root/.cache/huggingface/hub/models--TinyLlama--TinyLlama-1.1B-intermediate-step-1431k-3T/snapshots/036fa4651240b9a1487f709833b9e4b96b4c1574",3  "architectures": [4    "LlamaForCausalLM"5  ],6  "attention_bias": false,7  "attention_dropout": 0.0,8  "bos_token_id": 1,9  "eos_token_id": 2,10  "hidden_act": "silu",11  "hidden_size": 2048,12  "initializer_range": 0.02,13  "intermediate_size": 5632,14  "max_position_embeddings": 2048,15  "model_type": "llama",16  "num_attention_heads": 32,17  "num_hidden_layers": 22,18  "num_key_value_heads": 4,19  "pretraining_tp": 1,20  "rms_norm_eps": 1e-05,21  "rope_scaling": null,22  "rope_theta": 10000.0,23  "tie_word_embeddings": false,24  "torch_dtype": "float16",25  "transformers_version": "4.39.0",26  "use_cache": true,27  "vocab_size": 32000,28  "quantization_config": {29    "quantization_config": {30      "config_groups": {31        "group_0": {32          "input_activations": {33            "block_structure": null,34            "dynamic": false,35            "group_size": null,36            "num_bits": 8,37            "observer": "minmax",38            "observer_kwargs": {},39            "strategy": "tensor",40            "symmetric": true,41            "type": "int"42          },43          "output_activations": null,44          "targets": [45            "Linear"46          ],47          "weights": {48            "block_structure": null,49            "dynamic": false,50            "group_size": null,51            "num_bits": 8,52            "observer": "minmax",53            "observer_kwargs": {},54            "strategy": "tensor",55            "symmetric": true,56            "type": "int"57          }58        }59      },60      "format": "int-quantized",61      "global_compression_ratio": 1.4583332397611055,62      "ignore": [63        "lm_head"64      ],65      "quant_method": "sparseml",66      "quantization_status": "frozen"67    },68    "sparsity_config": {69      "format": "dense",70      "global_sparsity": 7.8259900429979625,71      "registry_requires_subclass": false,72      "sparsity_structure": "0:0"73    },74    "quant_method": "compressed-tensors"75  }76}