{ "_name_or_path": "/raid/sunilruf/alpha_ai_engine/resources/evaluation_test/Quantize/Mistral_Nemo_ultrachat_int8_v2", "architectures": [ "MistralForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 1, "compression_config": { "config_groups": { "group_0": { "input_activations": { "block_structure": null, "dynamic": true, "group_size": null, "num_bits": 8, "observer": "memoryless", "observer_kwargs": {}, "strategy": "token", "symmetric": true, "type": "int" }, "output_activations": null, "targets": [ "Linear" ], "weights": { "block_structure": null, "dynamic": false, "group_size": null, "num_bits": 8, "observer": "minmax", "observer_kwargs": {}, "strategy": "channel", "symmetric": true, "type": "int" } } }, "format": "int-quantized", "global_compression_ratio": 1.2401153158852773, "ignore": [ "lm_head" ], "kv_cache_scheme": null, "quant_method": "compressed-tensors", "quantization_status": "frozen" }, "eos_token_id": 2, "head_dim": 128, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 1024000, "model_type": "mistral", "num_attention_heads": 32, "num_hidden_layers": 40, "num_key_value_heads": 8, "quantization_config": { "_load_in_4bit": false, "_load_in_8bit": true, "bnb_4bit_compute_dtype": "float32", "bnb_4bit_quant_storage": "uint8", "bnb_4bit_quant_type": "fp4", "bnb_4bit_use_double_quant": false, "llm_int8_enable_fp32_cpu_offload": false, "llm_int8_has_fp16_weight": false, "llm_int8_skip_modules": null, "llm_int8_threshold": 6.0, "load_in_4bit": false, "load_in_8bit": true, "quant_method": "bitsandbytes" }, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.43.4", "use_cache": true, "vocab_size": 131072 }