qgallouedec's picture
qgallouedec HF Staff
Upload DeepseekV4ForCausalLM (#5)
5db63c1
{
"architectures": [
"DeepseekV4ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 0,
"compress_ratios": [
0,
0,
4,
128
],
"compress_rope_parameters": {
"beta_fast": 32,
"beta_slow": 1,
"factor": 16,
"original_max_position_embeddings": 65536,
"partial_rotary_factor": 0.125,
"rope_theta": 160000.0,
"rope_type": "yarn",
"type": "yarn"
},
"compress_rope_theta": 160000.0,
"dtype": "bfloat16",
"eos_token_id": 1,
"first_k_dense_replace": 2,
"hc_eps": 1e-06,
"hc_mult": 4,
"hc_sinkhorn_iters": 20,
"head_dim": 512,
"hidden_act": "silu",
"hidden_size": 8,
"index_head_dim": 128,
"index_n_heads": 64,
"index_topk": 512,
"initializer_range": 0.02,
"intermediate_size": 32,
"kv_lora_rank": null,
"max_position_embeddings": 1048576,
"model_type": "deepseek_v4",
"moe_intermediate_size": 2048,
"n_group": null,
"n_routed_experts": 4,
"n_shared_experts": 1,
"norm_topk_prob": true,
"num_attention_heads": 4,
"num_experts_per_tok": 2,
"num_hash_layers": 3,
"num_hidden_layers": 4,
"num_key_value_heads": 1,
"num_nextn_predict_layers": 1,
"o_groups": 8,
"o_lora_rank": 1024,
"output_router_logits": false,
"pad_token_id": null,
"partial_rotary_factor": 0.125,
"pretraining_tp": 1,
"q_lora_rank": 1024,
"qk_nope_head_dim": 448,
"qk_rope_head_dim": 64,
"rms_norm_eps": 1e-06,
"rope_interleave": true,
"rope_parameters": {
"beta_fast": 32,
"beta_slow": 1,
"factor": 16,
"original_max_position_embeddings": 65536,
"partial_rotary_factor": 0.125,
"rope_theta": 10000.0,
"rope_type": "yarn",
"type": "yarn"
},
"rope_theta": 10000.0,
"routed_scaling_factor": 1.5,
"router_aux_loss_coef": 0.001,
"router_jitter_noise": 0.0,
"scoring_func": "sqrtsoftplus",
"sliding_window": 128,
"swiglu_limit": 10.0,
"tie_word_embeddings": false,
"topk_group": null,
"topk_method": "noaux_tc",
"transformers_version": "5.7.0.dev0",
"use_cache": true,
"v_head_dim": null,
"vocab_size": 129280
}