| { |
| "architectures": [ |
| "DeepseekV4ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 0, |
| "compress_ratios": [ |
| 0, |
| 0, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 0, |
| 0, |
| 0 |
| ], |
| "compress_rope_theta": 160000, |
| "dspark_block_size": 5, |
| "dspark_markov_rank": 256, |
| "dspark_noise_token_id": 128799, |
| "dspark_target_layer_ids": [ |
| 40, |
| 41, |
| 42 |
| ], |
| "eos_token_id": 1, |
| "expert_dtype": "fp4", |
| "hc_eps": 1e-06, |
| "hc_mult": 4, |
| "hc_sinkhorn_iters": 20, |
| "head_dim": 512, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "index_head_dim": 128, |
| "index_n_heads": 64, |
| "index_topk": 512, |
| "initializer_range": 0.02, |
| "max_position_embeddings": 1048576, |
| "model_type": "deepseek_v4", |
| "moe_intermediate_size": 2048, |
| "n_routed_experts": 160, |
| "n_shared_experts": 1, |
| "norm_topk_prob": true, |
| "num_attention_heads": 64, |
| "num_experts_per_tok": 6, |
| "num_hash_layers": 3, |
| "num_hidden_layers": 43, |
| "num_key_value_heads": 1, |
| "num_nextn_predict_layers": 1, |
| "o_groups": 8, |
| "o_lora_rank": 1024, |
| "q_lora_rank": 1024, |
| "qk_rope_head_dim": 64, |
| "quantization_config": { |
| "activation_scheme": "dynamic", |
| "fmt": "e4m3", |
| "quant_method": "fp8", |
| "scale_fmt": "ue8m0", |
| "weight_block_size": [ |
| 128, |
| 128 |
| ] |
| }, |
| "reap_pruning": { |
| "backbone_layers": 43, |
| "built_at_unix": 1785518256, |
| "dspark_mtp_target_layers": [ |
| 40, |
| 41, |
| 42 |
| ], |
| "hash_routed_layers": [ |
| 0, |
| 1, |
| 2 |
| ], |
| "kept_experts_per_layer": 160, |
| "method": "REAP transferred ranking with router identity alignment", |
| "original_experts_per_layer": 256, |
| "prior_observation_model": "deepseek-ai/DeepSeek-V4-Flash", |
| "prior_observation_revision": "60d8d70770c6776ff598c94bb586a859a38244f1", |
| "prior_observation_snapshot": { |
| "all_experts_observed": true, |
| "available_rows_used": 21289, |
| "category_counts": { |
| "agentic_tool_trajectory": 2253, |
| "code_generation": 4096, |
| "reasoning_code": 2676, |
| "reasoning_math": 4072, |
| "reasoning_science": 4096, |
| "tool_calling": 4096 |
| }, |
| "readme_advertised_full_rows": 24576, |
| "repo_id": "0xSero/deepseek-v4-flash-reap-observations-v2", |
| "snapshot_label": "partial-v2-21289" |
| }, |
| "prior_plan_sha256": "2837dc8cd0f7512c111bd3a2c9c41278f715ded5965eb01889652ef8e465e1b0", |
| "router_alignment": { |
| "hash_tid2eid_equal_fraction": [ |
| 1.0, |
| 1.0, |
| 1.0 |
| ], |
| "identity_nearest_all": true, |
| "layers": 43, |
| "same_index_cos_mean_min": 0.9923683404922485, |
| "same_index_cos_min_global": 0.9460793733596802 |
| }, |
| "source_model": "deepseek-ai/DeepSeek-V4-Flash-0731", |
| "source_revision": "9e165c30e2704aec5d9d593cce3eebd58bbef1cb" |
| }, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": { |
| "beta_fast": 32, |
| "beta_slow": 1, |
| "factor": 16, |
| "original_max_position_embeddings": 65536, |
| "type": "yarn" |
| }, |
| "rope_theta": 10000, |
| "routed_scaling_factor": 1.5, |
| "scoring_func": "sqrtsoftplus", |
| "sliding_window": 128, |
| "swiglu_limit": 10.0, |
| "tie_word_embeddings": false, |
| "topk_method": "noaux_tc", |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.57.1", |
| "use_cache": true, |
| "vocab_size": 129280 |
| } |
|
|
