Upload folder using huggingface_hub

config.json

@@ -0,0 +1,89 @@
+{
+  "architectures": [
+    "DeepseekV4ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "compress_rates": {
+    "compressed_sparse_attention": 4,
+    "heavily_compressed_attention": 128
+  },
+  "compress_rope_theta": 160000,
+  "dtype": "bfloat16",
+  "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,
+  "layer_types": [
+    "heavily_compressed_attention",
+    "compressed_sparse_attention",
+    "sliding_attention"
+  ],
+  "max_position_embeddings": 1048576,
+  "mlp_bias": false,
+  "mlp_layer_types": [
+    "hash_moe",
+    "moe",
+    "moe"
+  ],
+  "model_type": "deepseek_v4",
+  "moe_intermediate_size": 2048,
+  "n_routed_experts": 16,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 64,
+  "num_experts_per_tok": 6,
+  "num_hidden_layers": 3,
+  "num_key_value_heads": 1,
+  "num_nextn_predict_layers": 0,
+  "o_groups": 8,
+  "o_lora_rank": 1024,
+  "output_router_logits": false,
+  "pad_token_id": null,
+  "partial_rotary_factor": 0.125,
+  "q_lora_rank": 1024,
+  "qk_rope_head_dim": 64,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "compress": {
+      "attention_factor": 1.0,
+      "beta_fast": 32,
+      "beta_slow": 1,
+      "factor": 16,
+      "original_max_position_embeddings": 65536,
+      "partial_rotary_factor": 0.125,
+      "rope_theta": 160000,
+      "rope_type": "yarn",
+      "type": "yarn"
+    },
+    "main": {
+      "partial_rotary_factor": 0.125,
+      "rope_theta": 10000,
+      "rope_type": "default"
+    },
+    "partial_rotary_factor": 0.125,
+    "rope_theta": 10000,
+    "rope_type": "default"
+  },
+  "rope_theta": 10000,
+  "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_method": "noaux_tc",
+  "transformers_version": "5.8.0.dev0",
+  "use_cache": true,
+  "vocab_size": 129280
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "do_sample": true,
+  "eos_token_id": 1,
+  "temperature": 1.0,
+  "top_p": 1.0,
+  "transformers_version": "5.8.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40d53fdb93a3abdf014f7683f4476d49b5527fc2d9af4fb0a76561ba22fa85a3
+size 5380457518