| { |
| "architectures": [ |
| "NanbeigeForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "configuration_nanbeige.NanbeigeConfig", |
| "AutoModel": "modeling_nanbeige.NanbeigeModel", |
| "AutoModelForCausalLM": "modeling_nanbeige.NanbeigeForCausalLM" |
| }, |
| "bos_token_id": 166100, |
| "depth_attention_recent_window": 0, |
| "depth_attention_static_anchor_once": true, |
| "depth_attention_stride": null, |
| "dtype": "bfloat16", |
| "emb_neighbor_num": null, |
| "emb_split_num": null, |
| "emb_tp_num": null, |
| "enable_depth_attention": false, |
| "enable_double_loop_split": false, |
| "enable_h_res_identity": false, |
| "enable_hyper_connection": false, |
| "enable_mhc": false, |
| "eos_token_id": 166101, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 3072, |
| "initializer_range": 0.02, |
| "insert_ngram_layer_idx": [], |
| "intermediate_size": 10752, |
| "kv_channels": 128, |
| "loop_loss_weights": [], |
| "loop_middle_layers": null, |
| "loop_share_kv": false, |
| "max_position_embeddings": 262144, |
| "mhc_diff_for_loop": false, |
| "mhc_double_stream_position_for_loop": null, |
| "mhc_identity_nohresparam": false, |
| "mhc_init_gating_factor": 0.01, |
| "mhc_sinkhorn_iterations": 20, |
| "mlp_bias": false, |
| "model_type": "nanbeige", |
| "ngram_compressed_tokenizer": false, |
| "ngram_embedding_hidden_size": null, |
| "ngram_fused_mode": "average", |
| "ngram_insert_all_layers": false, |
| "ngram_layer_downproject_size": null, |
| "ngram_mod_force_prime": false, |
| "ngram_vocab_size_ratio": null, |
| "num_attention_heads": 48, |
| "num_hidden_layers": 22, |
| "num_key_value_heads": 8, |
| "num_loops": 2, |
| "num_residual_streams": 4, |
| "pad_token_id": 0, |
| "pretraining_tp": 1, |
| "qk_layernorm": false, |
| "quantization_config": { |
| "config_groups": { |
| "group_0": { |
| "format": "float-quantized", |
| "input_activations": { |
| "actorder": null, |
| "block_structure": null, |
| "dynamic": true, |
| "group_size": null, |
| "num_bits": 8, |
| "observer": null, |
| "observer_kwargs": {}, |
| "scale_dtype": null, |
| "strategy": "token", |
| "symmetric": true, |
| "type": "float", |
| "zp_dtype": null |
| }, |
| "output_activations": null, |
| "targets": [ |
| "Linear" |
| ], |
| "weights": { |
| "actorder": null, |
| "block_structure": null, |
| "dynamic": false, |
| "group_size": null, |
| "num_bits": 8, |
| "observer": "memoryless_minmax", |
| "observer_kwargs": {}, |
| "scale_dtype": null, |
| "strategy": "channel", |
| "symmetric": true, |
| "type": "float", |
| "zp_dtype": null |
| } |
| } |
| }, |
| "format": "float-quantized", |
| "global_compression_ratio": null, |
| "ignore": [ |
| "lm_head" |
| ], |
| "kv_cache_scheme": null, |
| "quant_method": "compressed-tensors", |
| "quantization_status": "compressed", |
| "sparsity_config": {}, |
| "transform_config": {}, |
| "version": "0.17.1" |
| }, |
| "rms_norm_eps": 1e-05, |
| "rope_parameters": null, |
| "rope_theta": 70000000, |
| "skip_loop_final_norm": false, |
| "skip_ngram_for_input": false, |
| "tie_word_embeddings": false, |
| "transformers_version": "5.10.1", |
| "use_cache": true, |
| "vocab_size": 166144 |
| } |
