{ "architectures": [ "MuseGlimmerAssistantModel" ], "attention_dropout": 0, "block_size": 16, "bos_token_id": 200000, "dtype": "bfloat16", "eos_token_id": 200001, "head_dim": 128, "hidden_act": "silu", "hidden_size": 6656, "intermediate_size": 19968, "layer_types": [ "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention" ], "mask_token_id": 201818, "max_position_embeddings": 131072, "model_type": "muse_glimmer_assistant", "num_attention_heads": 32, "num_hidden_layers": 5, "num_key_value_heads": 8, "pad_token_id": 200018, "quantization_config": { "bits": 4, "checkpoint_format": "gptq", "desc_act": false, "format": "gptq", "group_size": 128, "lm_head": false, "meta": { "act_group_aware": true, "auto_forward_data_parallel": true, "damp_auto_increment": 0.01, "damp_percent": 0.05, "dense_vram_strategy": "exclusive", "dense_vram_strategy_devices": null, "fallback": { "smooth": null, "strategy": "rtn", "threshold": "0.5%" }, "foem": null, "gc_mode": "interval", "gptaq": null, "hessian": { "chunk_bytes": null, "chunk_size": null, "staging_dtype": "float32" }, "mock_quantization": false, "moe_vram_strategy": "exclusive", "moe_vram_strategy_devices": null, "mse": 0.0, "offload_to_disk": true, "offload_to_disk_path": "/tmp/muse-dflash-assistant-gptq-offload", "pack_impl": "cpu", "quantizer": [ "gptqmodel:7.3.2" ], "static_groups": false, "true_sequential": true, "uri": "https://github.com/modelcloud/gptqmodel", "wait_for_submodule_finalizers": false }, "method": "gptq", "modules_in_block_to_quantize": [ "self_attn.qkv_proj", "self_attn.o_proj", "mlp.gate_up_proj", "mlp.down_proj" ], "pack_dtype": "int32", "quant_method": "gptq", "sym": true }, "rms_norm_eps": 1e-05, "rope_parameters": { "rope_theta": 500000.0, "rope_type": "default" }, "sliding_window": 2048, "target_layer_ids": [ 1, 13, 25, 37, 49 ], "transformers_version": "5.15.1", "use_cache": false }