{ "architectures": [ "Qwen2MoeForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "decoder_sparse_step": 1, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 5632, "max_position_embeddings": 32768, "max_window_layers": 21, "model_type": "qwen2_moe", "moe_intermediate_size": 1408, "norm_topk_prob": false, "num_attention_heads": 16, "num_experts": 60, "num_experts_per_tok": 4, "num_hidden_layers": 24, "num_key_value_heads": 16, "output_router_logits": false, "quantization_config": { "batch_size": 1, "bits": 4, "block_name_to_quantize": null, "cache_block_outputs": true, "damp_percent": 0.01, "dataset": null, "desc_act": false, "exllama_config": { "version": 1 }, "group_size": 128, "max_input_length": null, "model_seqlen": null, "module_name_preceding_first_block": null, "modules_in_block_to_quantize": [ [ "self_attn.k_proj", "self_attn.v_proj", "self_attn.q_proj" ], [ "self_attn.o_proj" ], [ "mlp.shared_expert.up_proj", "mlp.shared_expert.gate_proj" ], [ "mlp.shared_expert.down_proj" ], [ "mlp.experts.0.up_proj", "mlp.experts.1.up_proj", "mlp.experts.2.up_proj", "mlp.experts.3.up_proj", "mlp.experts.4.up_proj", "mlp.experts.5.up_proj", "mlp.experts.6.up_proj", "mlp.experts.7.up_proj", "mlp.experts.8.up_proj", "mlp.experts.9.up_proj", "mlp.experts.10.up_proj", "mlp.experts.11.up_proj", "mlp.experts.12.up_proj", "mlp.experts.13.up_proj", "mlp.experts.14.up_proj", "mlp.experts.15.up_proj", "mlp.experts.16.up_proj", "mlp.experts.17.up_proj", "mlp.experts.18.up_proj", "mlp.experts.19.up_proj", "mlp.experts.20.up_proj", "mlp.experts.21.up_proj", "mlp.experts.22.up_proj", "mlp.experts.23.up_proj", "mlp.experts.24.up_proj", "mlp.experts.25.up_proj", "mlp.experts.26.up_proj", "mlp.experts.27.up_proj", "mlp.experts.28.up_proj", "mlp.experts.29.up_proj", "mlp.experts.30.up_proj", "mlp.experts.31.up_proj", "mlp.experts.32.up_proj", "mlp.experts.33.up_proj", "mlp.experts.34.up_proj", "mlp.experts.35.up_proj", "mlp.experts.36.up_proj", "mlp.experts.37.up_proj", "mlp.experts.38.up_proj", "mlp.experts.39.up_proj", "mlp.experts.40.up_proj", "mlp.experts.41.up_proj", "mlp.experts.42.up_proj", "mlp.experts.43.up_proj", "mlp.experts.44.up_proj", "mlp.experts.45.up_proj", "mlp.experts.46.up_proj", "mlp.experts.47.up_proj", "mlp.experts.48.up_proj", "mlp.experts.49.up_proj", "mlp.experts.50.up_proj", "mlp.experts.51.up_proj", "mlp.experts.52.up_proj", "mlp.experts.53.up_proj", "mlp.experts.54.up_proj", "mlp.experts.55.up_proj", "mlp.experts.56.up_proj", "mlp.experts.57.up_proj", "mlp.experts.58.up_proj", "mlp.experts.59.up_proj", "mlp.experts.0.gate_proj", "mlp.experts.1.gate_proj", "mlp.experts.2.gate_proj", "mlp.experts.3.gate_proj", "mlp.experts.4.gate_proj", "mlp.experts.5.gate_proj", "mlp.experts.6.gate_proj", "mlp.experts.7.gate_proj", "mlp.experts.8.gate_proj", "mlp.experts.9.gate_proj", "mlp.experts.10.gate_proj", "mlp.experts.11.gate_proj", "mlp.experts.12.gate_proj", "mlp.experts.13.gate_proj", "mlp.experts.14.gate_proj", "mlp.experts.15.gate_proj", "mlp.experts.16.gate_proj", "mlp.experts.17.gate_proj", "mlp.experts.18.gate_proj", "mlp.experts.19.gate_proj", "mlp.experts.20.gate_proj", "mlp.experts.21.gate_proj", "mlp.experts.22.gate_proj", "mlp.experts.23.gate_proj", "mlp.experts.24.gate_proj", "mlp.experts.25.gate_proj", "mlp.experts.26.gate_proj", "mlp.experts.27.gate_proj", "mlp.experts.28.gate_proj", "mlp.experts.29.gate_proj", "mlp.experts.30.gate_proj", "mlp.experts.31.gate_proj", "mlp.experts.32.gate_proj", "mlp.experts.33.gate_proj", "mlp.experts.34.gate_proj", "mlp.experts.35.gate_proj", "mlp.experts.36.gate_proj", "mlp.experts.37.gate_proj", "mlp.experts.38.gate_proj", "mlp.experts.39.gate_proj", "mlp.experts.40.gate_proj", "mlp.experts.41.gate_proj", "mlp.experts.42.gate_proj", "mlp.experts.43.gate_proj", "mlp.experts.44.gate_proj", "mlp.experts.45.gate_proj", "mlp.experts.46.gate_proj", "mlp.experts.47.gate_proj", "mlp.experts.48.gate_proj", "mlp.experts.49.gate_proj", "mlp.experts.50.gate_proj", "mlp.experts.51.gate_proj", "mlp.experts.52.gate_proj", "mlp.experts.53.gate_proj", "mlp.experts.54.gate_proj", "mlp.experts.55.gate_proj", "mlp.experts.56.gate_proj", "mlp.experts.57.gate_proj", "mlp.experts.58.gate_proj", "mlp.experts.59.gate_proj" ], [ "mlp.experts.0.down_proj", "mlp.experts.1.down_proj", "mlp.experts.2.down_proj", "mlp.experts.3.down_proj", "mlp.experts.4.down_proj", "mlp.experts.5.down_proj", "mlp.experts.6.down_proj", "mlp.experts.7.down_proj", "mlp.experts.8.down_proj", "mlp.experts.9.down_proj", "mlp.experts.10.down_proj", "mlp.experts.11.down_proj", "mlp.experts.12.down_proj", "mlp.experts.13.down_proj", "mlp.experts.14.down_proj", "mlp.experts.15.down_proj", "mlp.experts.16.down_proj", "mlp.experts.17.down_proj", "mlp.experts.18.down_proj", "mlp.experts.19.down_proj", "mlp.experts.20.down_proj", "mlp.experts.21.down_proj", "mlp.experts.22.down_proj", "mlp.experts.23.down_proj", "mlp.experts.24.down_proj", "mlp.experts.25.down_proj", "mlp.experts.26.down_proj", "mlp.experts.27.down_proj", "mlp.experts.28.down_proj", "mlp.experts.29.down_proj", "mlp.experts.30.down_proj", "mlp.experts.31.down_proj", "mlp.experts.32.down_proj", "mlp.experts.33.down_proj", "mlp.experts.34.down_proj", "mlp.experts.35.down_proj", "mlp.experts.36.down_proj", "mlp.experts.37.down_proj", "mlp.experts.38.down_proj", "mlp.experts.39.down_proj", "mlp.experts.40.down_proj", "mlp.experts.41.down_proj", "mlp.experts.42.down_proj", "mlp.experts.43.down_proj", "mlp.experts.44.down_proj", "mlp.experts.45.down_proj", "mlp.experts.46.down_proj", "mlp.experts.47.down_proj", "mlp.experts.48.down_proj", "mlp.experts.49.down_proj", "mlp.experts.50.down_proj", "mlp.experts.51.down_proj", "mlp.experts.52.down_proj", "mlp.experts.53.down_proj", "mlp.experts.54.down_proj", "mlp.experts.55.down_proj", "mlp.experts.56.down_proj", "mlp.experts.57.down_proj", "mlp.experts.58.down_proj", "mlp.experts.59.down_proj" ] ], "pad_token_id": null, "quant_method": "gptq", "sym": true, "tokenizer": null, "true_sequential": true, "use_cuda_fp16": false, "use_exllama": true }, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "router_aux_loss_coef": 0.001, "shared_expert_intermediate_size": 5632, "sliding_window": 32768, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.39.0.dev0", "use_cache": true, "use_sliding_window": false, "vocab_size": 151936 }