| { |
| "_attn_implementation_autoset": false, |
| "architectures": [ |
| "DeepseekV3ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "configuration_deepseek.DeepseekV3Config", |
| "AutoModel": "modeling_deepseek.DeepseekV3Model", |
| "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM" |
| }, |
| "aux_loss_alpha": 0.001, |
| "bos_token_id": 163584, |
| "dtype": "bfloat16", |
| "eos_token_id": 163586, |
| "ep_size": 1, |
| "first_k_dense_replace": 1, |
| "hidden_act": "silu", |
| "hidden_size": 7168, |
| "initializer_range": 0.02, |
| "intermediate_size": 18432, |
| "kv_lora_rank": 512, |
| "max_position_embeddings": 262144, |
| "model_type": "deepseek_v3", |
| "moe_intermediate_size": 2048, |
| "moe_layer_freq": 1, |
| "n_group": 1, |
| "n_routed_experts": 384, |
| "n_shared_experts": 1, |
| "norm_topk_prob": true, |
| "num_attention_heads": 64, |
| "num_experts_per_tok": 8, |
| "num_hidden_layers": 61, |
| "num_key_value_heads": 64, |
| "num_nextn_predict_layers": 0, |
| "pad_token_id": 163839, |
| "pretraining_tp": 1, |
| "q_lora_rank": 1536, |
| "qk_nope_head_dim": 128, |
| "qk_rope_head_dim": 64, |
| "quantization_config": { |
| "config_groups": { |
| "FP8_BLOCK": { |
| "format": "float-quantized", |
| "input_activations": { |
| "actorder": null, |
| "block_structure": null, |
| "dynamic": true, |
| "group_size": 128, |
| "num_bits": 8, |
| "observer": null, |
| "observer_kwargs": {}, |
| "strategy": "group", |
| "symmetric": true, |
| "type": "float" |
| }, |
| "output_activations": null, |
| "targets": [ |
| "Linear" |
| ], |
| "weights": { |
| "actorder": null, |
| "block_structure": [ |
| 128, |
| 128 |
| ], |
| "dynamic": false, |
| "group_size": null, |
| "num_bits": 8, |
| "observer": "static_minmax", |
| "observer_kwargs": {}, |
| "strategy": "block", |
| "symmetric": true, |
| "type": "float" |
| } |
| } |
| }, |
| "format": "float-quantized", |
| "global_compression_ratio": null, |
| "ignore": [ |
| "re:.*gate$", |
| "lm_head", |
| "re:.*kv_a_proj_with_mqa$", |
| "re:.*q_a_proj$", |
| "model.embed_tokens" |
| ], |
| "kv_cache_scheme": null, |
| "quant_method": "compressed-tensors", |
| "quantization_status": "compressed", |
| "sparsity_config": {}, |
| "transform_config": {}, |
| "version": "0.12.3.a20251030" |
| }, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": { |
| "beta_fast": 1.0, |
| "beta_slow": 1.0, |
| "factor": 64.0, |
| "mscale": 1.0, |
| "mscale_all_dim": 1.0, |
| "original_max_position_embeddings": 4096, |
| "type": "yarn" |
| }, |
| "rope_theta": 50000.0, |
| "routed_scaling_factor": 2.827, |
| "scoring_func": "sigmoid", |
| "seq_aux": true, |
| "tie_word_embeddings": false, |
| "topk_group": 1, |
| "topk_method": "noaux_tc", |
| "transformers_version": "4.57.1", |
| "use_cache": true, |
| "v_head_dim": 128, |
| "vocab_size": 163840 |
| } |
