tiny-random/deepseek-v4-fp4-fp8

1{2  "architectures": [3    "DeepseekV4ForCausalLM"4  ],5  "attention_bias": true,6  "attention_dropout": 0.0,7  "bos_token_id": 0,8  "eos_token_id": 1,9  "expert_dtype": "fp4",10  "hc_eps": 1e-06,11  "hc_mult": 4,12  "hc_sinkhorn_iters": 20,13  "head_dim": 512,14  "hidden_act": "silu",15  "hidden_size": 256,16  "index_head_dim": 128,17  "index_n_heads": 32,18  "index_topk": 1024,19  "initializer_range": 0.02,20  "max_position_embeddings": 1048576,21  "model_type": "deepseek_v4",22  "moe_intermediate_size": 256,23  "n_routed_experts": 128,24  "n_shared_experts": 1,25  "norm_topk_prob": true,26  "num_attention_heads": 4,27  "num_experts_per_tok": 6,28  "num_hidden_layers": 7,29  "num_hash_layers": 3,30  "num_key_value_heads": 1,31  "num_nextn_predict_layers": 1,32  "o_groups": 2,33  "o_lora_rank": 128,34  "q_lora_rank": 128,35  "qk_rope_head_dim": 64,36  "quantization_config": {37    "activation_scheme": "dynamic",38    "fmt": "e4m3",39    "quant_method": "fp8",40    "scale_fmt": "ue8m0",41    "weight_block_size": [42      128,43      12844    ]45  },46  "rms_norm_eps": 1e-06,47  "rope_scaling": {48    "beta_fast": 32,49    "beta_slow": 1,50    "factor": 16,51    "original_max_position_embeddings": 65536,52    "type": "yarn"53  },54  "rope_theta": 10000,55  "routed_scaling_factor": 2.5,56  "scoring_func": "sqrtsoftplus",57  "sliding_window": 128,58  "swiglu_limit": 10.0,59  "tie_word_embeddings": false,60  "topk_method": "noaux_tc",61  "torch_dtype": "bfloat16",62  "transformers_version": "4.57.1",63  "use_cache": true,64  "vocab_size": 129280,65  "compress_rope_theta": 160000,66  "compress_ratios": [67    128,68    128,69    4,70    128,71    4,72    128,73    4,74    075  ]76}