Update config.json

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "/data5/yliu7/HF_HOME/DeepSeek-R1-bf16/DeepSeek-R1-bf16",
   "architectures": [
     "DeepseekV3ForCausalLM"
   ],
@@ -32,7 +33,6 @@
   "num_hidden_layers": 61,
   "num_key_value_heads": 128,
   "num_nextn_predict_layers": 1,
-  "pad_token_id": 128815,
   "pretraining_tp": 1,
   "q_lora_rank": 1536,
   "qk_nope_head_dim": 128,
@@ -45,7 +45,7 @@
           "block_structure": null,
           "dynamic": "local",
           "group_size": 32,
-	  "is_mx": true,
+          "is_mx": true,
           "num_bits": 8,
           "observer": "minmax",
           "observer_kwargs": {},
@@ -62,8 +62,8 @@
           "block_structure": null,
           "dynamic": false,
           "group_size": 32,
+          "is_mx": true,
           "num_bits": 8,
-	  "is_mx": true,
           "observer": "minmax",
           "observer_kwargs": {},
           "strategy": "tensor_group",
@@ -72,7 +72,7 @@
         }
       }
     },
-    "format": "nvfp4-pack-quantized",
+    "format": "float-quantized",
     "global_compression_ratio": null,
     "ignore": [
       "lm_head"
@@ -99,8 +99,7 @@
   "topk_group": 4,
   "topk_method": "noaux_tc",
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.53.3",
-  "unsloth_fixed": true,
+  "transformers_version": "4.47.0",
   "use_cache": true,
   "v_head_dim": 128,
   "vocab_size": 129280