RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16

1{2  "_name_or_path": "/network/alexandre/models/mistralai__Mistral-Nemo-Instruct-2407",3  "architectures": [4    "MistralForCausalLM"5  ],6  "attention_dropout": 0.0,7  "bos_token_id": 1,8  "eos_token_id": 2,9  "head_dim": 128,10  "hidden_act": "silu",11  "hidden_size": 5120,12  "initializer_range": 0.02,13  "intermediate_size": 14336,14  "max_position_embeddings": 1024000,15  "model_type": "mistral",16  "num_attention_heads": 32,17  "num_hidden_layers": 40,18  "num_key_value_heads": 8,19  "rms_norm_eps": 1e-05,20  "rope_theta": 1000000.0,21  "sliding_window": null,22  "tie_word_embeddings": false,23  "torch_dtype": "bfloat16",24  "transformers_version": "4.43.0.dev0",25  "use_cache": true,26  "vocab_size": 131072,27  "quantization_config": {28    "config_groups": {29      "group_0": {30        "input_activations": null,31        "output_activations": null,32        "targets": [33          "Linear"34        ],35        "weights": {36          "block_structure": null,37          "dynamic": false,38          "group_size": null,39          "num_bits": 8,40          "observer": "minmax",41          "observer_kwargs": {},42          "strategy": "channel",43          "symmetric": true,44          "type": "int"45        }46      }47    },48    "format": "pack-quantized",49    "global_compression_ratio": 1.4619965155281183,50    "ignore": [51      "lm_head"52    ],53    "kv_cache_scheme": null,54    "quant_method": "compressed-tensors",55    "quantization_status": "compressed",56    "sparsity_config": {}57  }58}59