Upload DeepseekV3ForCausalLM

config.json

@@ -4,8 +4,15 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_deepseek.DeepseekV3Config",
+    "AutoModel": "modeling_deepseek.DeepseekV3Model",
+    "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
+  },
   "bos_token_id": 0,
+  "dtype": "float32",
   "eos_token_id": 1,
+  "ep_size": 1,
   "first_k_dense_replace": 3,
   "head_dim": 64,
   "hidden_act": "silu",
@@ -13,9 +20,10 @@
   "initializer_range": 0.02,
   "intermediate_size": 32,
   "kv_lora_rank": 512,
-  "max_position_embeddings": 4096,
+  "max_position_embeddings": 163840,
   "model_type": "deepseek_v3",
   "moe_intermediate_size": 2048,
+  "moe_layer_freq": 1,
   "n_group": 8,
   "n_routed_experts": 256,
   "n_shared_experts": 1,
@@ -24,21 +32,41 @@
   "num_experts_per_tok": 8,
   "num_hidden_layers": 2,
   "num_key_value_heads": 2,
+  "num_nextn_predict_layers": 1,
   "pretraining_tp": 1,
   "q_lora_rank": 1536,
   "qk_head_dim": 192,
   "qk_nope_head_dim": 128,
   "qk_rope_head_dim": 64,
+  "quantization_config": {
+    "activation_scheme": "dynamic",
+    "fmt": "e4m3",
+    "quant_method": "fp8",
+    "weight_block_size": [
+      128,
+      128
+    ]
+  },
   "rms_norm_eps": 1e-06,
   "rope_interleave": true,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
+  "rope_scaling": {
+    "beta_fast": 32.0,
+    "beta_slow": 1.0,
+    "factor": 40.0,
+    "mscale": 1.0,
+    "mscale_all_dim": 1.0,
+    "original_max_position_embeddings": 4096,
+    "rope_type": "yarn",
+    "type": "yarn"
+  },
+  "rope_theta": 10000,
   "routed_scaling_factor": 2.5,
+  "scoring_func": "sigmoid",
   "tie_word_embeddings": false,
   "topk_group": 4,
-  "torch_dtype": "float32",
-  "transformers_version": "4.55.0.dev0",
+  "topk_method": "noaux_tc",
+  "transformers_version": "4.57.0.dev0",
   "use_cache": true,
   "v_head_dim": 128,
-  "vocab_size": 128818
+  "vocab_size": 129280
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 0,
   "eos_token_id": 1,
-  "transformers_version": "4.55.0.dev0"
+  "transformers_version": "4.57.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62f612c2df3eedce6aeecb7332b3a0095a68033234accf815a39ea1a6f52106f
-size 22069392
+oid sha256:8ce7d23aa9cca2b358889c05b0b453ee01de251c0a32c938bdb23bbe148e9173
+size 22098960