Upload DeepseekV4ForCausalLM

config.json

@@ -7,7 +7,8 @@
   "bos_token_id": 0,
   "compress_ratios": [
     0,
-    0
+    4,
+    128
   ],
   "compress_rope_parameters": {
     "partial_rotary_factor": 0.125,
@@ -17,7 +18,7 @@
   "compress_rope_theta": 160000.0,
   "dtype": "bfloat16",
   "eos_token_id": 1,
-  "first_k_dense_replace": null,
+  "first_k_dense_replace": 1,
   "hc_eps": 1e-06,
   "hc_mult": 4,
   "hc_sinkhorn_iters": 20,
@@ -34,13 +35,13 @@
   "model_type": "deepseek_v4",
   "moe_intermediate_size": 2048,
   "n_group": null,
-  "n_routed_experts": 256,
+  "n_routed_experts": 4,
   "n_shared_experts": 1,
   "norm_topk_prob": true,
   "num_attention_heads": 4,
-  "num_experts_per_tok": 6,
-  "num_hash_layers": 3,
-  "num_hidden_layers": 2,
+  "num_experts_per_tok": 2,
+  "num_hash_layers": 2,
+  "num_hidden_layers": 3,
   "num_key_value_heads": 2,
   "num_nextn_predict_layers": 1,
   "o_groups": 8,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53f6bf42b1d190e81a90dc7b9f30eaa4b3fa650313fe4785d26b4cb11bf7adef
-size 83997562
+oid sha256:e5c0682e334f5e114dc223c4196864ef67442228dcfe4eec24c953d386ecd5e6
+size 52073390