{ "architectures": [ "FuseGlmForCausalLM" ], "auto_map": { "AutoConfig": "configuration_fuse_glm.FuseGlmConfig", "AutoModelForCausalLM": "modeling_fuse_glm.FuseGlmForCausalLM" }, "block_auto_adjust_ff_dim": false, "block_dim": 2048, "block_ffn_dim_multiplier": 1.0, "block_mlp_init_scale": 1.0, "block_multiple_of": 256, "block_norm_eps": 1e-05, "block_out_init_scale": 1.0, "block_use_swiglu": true, "block_use_xavier_init": true, "bos_token_id": 124894, "conv_L_cache": 3, "conv_bias": false, "conv_dim": 2048, "conv_use_xavier_init": true, "dtype": "bfloat16", "eos_token_id": 124900, "full_attn_idxs": null, "fuse_glm_coding_enabled": true, "fuse_glm_expert_intermediate_size": 2048, "fuse_glm_gate_clamp_max": 10.0, "fuse_glm_hard_token_gate_at_eval": false, "fuse_glm_layer_indices": [ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29 ], "fuse_glm_num_experts": 16, "fuse_glm_output_router_diagnostics": false, "fuse_glm_residual_scale_max": 0.1, "fuse_glm_router_aux_loss_coef": 0.0, "fuse_glm_token_gate_bias": -4.0, "fuse_glm_token_gate_threshold": 0.5, "fuse_glm_top_k": 4, "fuse_glm_up_clamp_max": 10.0, "fuse_glm_up_clamp_min": -10.0, "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 10752, "layer_types": [ "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention" ], "max_position_embeddings": 131072, "model_type": "fuse_glm", "norm_eps": 1e-05, "num_attention_heads": 32, "num_heads": 32, "num_hidden_layers": 30, "num_key_value_heads": 8, "pad_token_id": 124893, "quantization_config": { "include_input_output_embeddings": false, "modules_to_not_convert": null, "quant_method": "torchao", "quant_type": { "default": { "_data": { "activation_dtype": { "_data": "float8_e4m3fn", "_type": "torch.dtype" }, "activation_value_lb": null, "activation_value_ub": null, "granularity": [ { "_data": {}, "_type": "PerTensor", "_version": 1 }, { "_data": {}, "_type": "PerTensor", "_version": 1 } ], "kernel_preference": { "_data": "AUTO", "_type": "KernelPreference" }, "mm_config": { "_data": { "emulate": false, "pad_inner_dim": false, "use_fast_accum": true }, "_type": "Float8MMConfig", "_version": 1 }, "set_inductor_config": true, "weight_dtype": { "_data": "float8_e4m3fn", "_type": "torch.dtype" } }, "_type": "Float8DynamicActivationFloat8WeightConfig", "_version": 2 } }, "untie_embedding_weights": false }, "rivet_coder": { "active_parameters_approx": 4210000000, "base_repo_id": "HCHs/RivetCoder-9B-A4B", "donor": "zai-org/GLM-5.3-Flash", "experts_per_layer": 16, "experts_per_token": 4, "host": "LiquidAI/LFM2.5-2.6B", "name": "RivetCoder-9B-A4B-FP8", "quantization": "TorchAO Float8DynamicActivationFloat8WeightConfig", "repo_id": "HCHs/RivetCoder-9B-A4B-FP8", "router_teacher": "qwen/qwen3.8-27b", "total_parameters_approx": 8740000000, "training_steps": 60 }, "rope_parameters": { "rope_theta": 10000000.0, "rope_type": "default" }, "tie_word_embeddings": true, "transformers_version": "5.16.1", "use_cache": true, "use_pos_enc": true, "vocab_size": 128000 }