upload

config.json

@@ -1,6 +1,6 @@
 {
   "architectures": [
-    "DeepseekV3Model"
+    "DeepseekV3ForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
@@ -13,7 +13,6 @@
   "eos_token_id": 1,
   "ep_size": 1,
   "first_k_dense_replace": 3,
-  "head_dim": 64,
   "hidden_act": "silu",
   "hidden_size": 32,
   "initializer_range": 0.02,
@@ -32,30 +31,17 @@
   "num_hidden_layers": 3,
   "num_key_value_heads": 128,
   "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": {
-    "beta_fast": 32.0,
-    "beta_slow": 1.0,
-    "factor": 40.0,
+    "beta_fast": 32,
+    "beta_slow": 1,
+    "factor": 40,
     "mscale": 1.0,
     "mscale_all_dim": 1.0,
     "original_max_position_embeddings": 4096,
-    "rope_type": "yarn",
     "type": "yarn"
   },
   "rope_theta": 10000,
@@ -65,7 +51,7 @@
   "topk_group": 4,
   "topk_method": "noaux_tc",
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.55.0",
+  "transformers_version": "4.46.3",
   "use_cache": true,
   "v_head_dim": 128,
   "vocab_size": 129280