Wfiles/MNLP_M2_quantized_model

1{2  "architectures": [3    "Qwen3Model"4  ],5  "attention_bias": false,6  "attention_dropout": 0.0,7  "bos_token_id": 151643,8  "eos_token_id": 151643,9  "head_dim": 128,10  "hidden_act": "silu",11  "hidden_size": 1024,12  "initializer_range": 0.02,13  "intermediate_size": 3072,14  "max_position_embeddings": 32768,15  "max_window_layers": 28,16  "model_type": "qwen3",17  "num_attention_heads": 16,18  "num_hidden_layers": 28,19  "num_key_value_heads": 8,20  "quantization_config": {21    "config_groups": {22      "group_0": {23        "input_activations": {24          "actorder": null,25          "block_structure": null,26          "dynamic": true,27          "group_size": null,28          "num_bits": 8,29          "observer": null,30          "observer_kwargs": {},31          "strategy": "token",32          "symmetric": true,33          "type": "int"34        },35        "output_activations": null,36        "targets": [37          "Linear"38        ],39        "weights": {40          "actorder": null,41          "block_structure": null,42          "dynamic": false,43          "group_size": null,44          "num_bits": 8,45          "observer": "minmax",46          "observer_kwargs": {},47          "strategy": "channel",48          "symmetric": true,49          "type": "int"50        }51      }52    },53    "format": "int-quantized",54    "global_compression_ratio": null,55    "ignore": [56      "lm_head"57    ],58    "kv_cache_scheme": null,59    "quant_method": "compressed-tensors",60    "quantization_status": "compressed",61    "sparsity_config": {}62  },63  "rms_norm_eps": 1e-06,64  "rope_scaling": null,65  "rope_theta": 1000000,66  "sliding_window": null,67  "tie_word_embeddings": true,68  "torch_dtype": "float16",69  "transformers_version": "4.51.3",70  "use_cache": false,71  "use_sliding_window": false,72  "vocab_size": 15193673}74