{ "_name_or_path": "/nm/drive0/alexandre/cache/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/0417f4babd26db0b5ed07c1d0bc85658ab526ea3", "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": 1.239800472368003, "ignore": [ "lm_head" ], "kv_cache_scheme": null, "quant_method": "compressed-tensors", "quantization_status": "frozen", "sparsity_config": { "format": "dense", "global_sparsity": 1.526963691632331, "registry_requires_subclass": false, "sparsity_structure": "unstructured" } }, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 32768, "model_type": "mistral", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.42.3", "use_cache": true, "vocab_size": 32768 }