| { |
| "architectures": [ |
| "LLaDA2MoeModelLM" |
| ], |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "configuration_llada2_moe.LLaDA2MoeConfig", |
| "AutoModel": "modeling_llada2_moe.LLaDA2MoeModel", |
| "AutoModelForCausalLM": "modeling_llada2_moe.LLaDA2MoeModelLM" |
| }, |
| "dtype": "bfloat16", |
| "embedding_dropout": 0.0, |
| "first_k_dense_replace": 1, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 2048, |
| "initializer_range": 0.02, |
| "intermediate_size": 5120, |
| "max_position_embeddings": 32768, |
| "max_window_layers": 28, |
| "model_type": "llada2_moe", |
| "moe_intermediate_size": 512, |
| "moe_router_enable_expert_bias": true, |
| "n_group": 8, |
| "norm_head": false, |
| "norm_softmax": false, |
| "norm_topk_prob": true, |
| "num_attention_heads": 16, |
| "num_experts": 256, |
| "num_experts_per_tok": 8, |
| "num_hidden_layers": 20, |
| "num_key_value_heads": 4, |
| "num_shared_experts": 1, |
| "output_dropout": 0.0, |
| "output_router_logits": false, |
| "pad_token_id": 156892, |
| "partial_rotary_factor": 0.5, |
| "quantization_config": { |
| "config_groups": { |
| "group_0": { |
| "format": "nvfp4-pack-quantized", |
| "input_activations": { |
| "actorder": null, |
| "block_structure": null, |
| "dynamic": "local", |
| "group_size": 16, |
| "num_bits": 4, |
| "observer": "static_minmax", |
| "observer_kwargs": {}, |
| "scale_dtype": "torch.float8_e4m3fn", |
| "strategy": "tensor_group", |
| "symmetric": true, |
| "type": "float", |
| "zp_dtype": null |
| }, |
| "output_activations": null, |
| "targets": [ |
| "Linear" |
| ], |
| "weights": { |
| "actorder": null, |
| "block_structure": null, |
| "dynamic": false, |
| "group_size": 16, |
| "num_bits": 4, |
| "observer": "memoryless_minmax", |
| "observer_kwargs": {}, |
| "scale_dtype": "torch.float8_e4m3fn", |
| "strategy": "tensor_group", |
| "symmetric": true, |
| "type": "float", |
| "zp_dtype": null |
| } |
| } |
| }, |
| "format": "nvfp4-pack-quantized", |
| "global_compression_ratio": null, |
| "ignore": [ |
| "lm_head" |
| ], |
| "kv_cache_scheme": null, |
| "quant_method": "compressed-tensors", |
| "quantization_status": "compressed", |
| "sparsity_config": {}, |
| "transform_config": {}, |
| "version": "0.16.0" |
| }, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": null, |
| "rope_theta": 600000, |
| "rotary_dim": 64, |
| "routed_scaling_factor": 2.5, |
| "router_dtype": "fp32", |
| "score_function": "sigmoid", |
| "sliding_window": 4096, |
| "tie_word_embeddings": false, |
| "topk_group": 4, |
| "transformers_version": "4.57.3", |
| "use_bias": false, |
| "use_cache": false, |
| "use_qk_norm": true, |
| "use_qkv_bias": false, |
| "use_rmsnorm": true, |
| "use_sliding_window": false, |
| "using_split_qkv_in_self_attention": false, |
| "vocab_size": 157184 |
| } |
