nm-testing/SmolLM-135M-Instruct-quantized.w4a16

1{2  "_name_or_path": "/home/shashata/.cache/huggingface/hub/models--HuggingFaceTB--SmolLM-135M-Instruct/snapshots/6f9ca38eaa51eb95a2daac3f940ca6091c64a7fb",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": 576,12  "initializer_range": 0.02,13  "intermediate_size": 1536,14  "max_position_embeddings": 2048,15  "mlp_bias": false,16  "model_type": "llama",17  "num_attention_heads": 9,18  "num_hidden_layers": 30,19  "num_key_value_heads": 3,20  "pad_token_id": 2,21  "pretraining_tp": 1,22  "rms_norm_eps": 1e-05,23  "rope_scaling": null,24  "rope_theta": 10000.0,25  "tie_word_embeddings": true,26  "torch_dtype": "float32",27  "transformers_version": "4.43.4",28  "use_cache": true,29  "vocab_size": 49152,30  "quantization_config": {31    "config_groups": {32      "group_0": {33        "input_activations": null,34        "output_activations": null,35        "targets": [36          "Linear"37        ],38        "weights": {39          "block_structure": null,40          "dynamic": false,41          "group_size": 64,42          "num_bits": 4,43          "observer": "minmax",44          "observer_kwargs": {},45          "strategy": "group",46          "symmetric": true,47          "type": "int"48        }49      }50    },51    "format": "pack-quantized",52    "global_compression_ratio": 2.21942975247817,53    "ignore": [54      "lm_head"55    ],56    "kv_cache_scheme": null,57    "quant_method": "compressed-tensors",58    "quantization_status": "compressed",59    "sparsity_config": {60      "format": "dense",61      "global_sparsity": 11.319185291205573,62      "registry_requires_subclass": false,63      "sparsity_structure": "unstructured"64    }65  }66}67