Update config.json

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "/data5/yliu7/HF_HOME/DeepSeek-R1-bf16/DeepSeek-R1-bf16",
   "architectures": [
     "DeepseekV3ForCausalLM"
   ],
@@ -14,7 +15,6 @@
   "eos_token_id": 1,
   "ep_size": 1,
   "first_k_dense_replace": 3,
-  "head_dim": 64,
   "hidden_act": "silu",
   "hidden_size": 7168,
   "initializer_range": 0.02,
@@ -33,40 +33,62 @@
   "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_head_dim": 192,
   "qk_nope_head_dim": 128,
   "qk_rope_head_dim": 64,
   "quantization_config": {
-    "autoround_version": "0.6.0",
-    "batch_size": 4,
-    "bits": 4,
-    "data_type": "mx_fp4e2m1",
-    "group_size": 32,
-    "low_gpu_mem_usage": true,
-    "packing_format": "mx_fp",
-    "quant_method": "auto-round",
-    "scale_calculation_mode": [
-      "even"
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": "local",
+          "group_size": 32,
+          "is_mx": true,
+          "num_bits": 4,
+          "observer": "minmax",
+          "observer_kwargs": {},
+          "strategy": "tensor_group",
+          "symmetric": true,
+          "type": "float"
+        },
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": 32,
+          "is_mx": true,
+          "num_bits": 4,
+          "observer": "minmax",
+          "observer_kwargs": {},
+          "strategy": "tensor_group",
+          "symmetric": true,
+          "type": "float"
+        }
+      }
+    },
+    "format": "float-quantized",
+    "global_compression_ratio": null,
+    "ignore": [
+      "lm_head"
     ],
-    "scale_format": [
-      "e8m0"
-    ],
-    "seqlen": 512,
-    "sym": true
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed"
   },
   "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,
@@ -77,8 +99,7 @@
   "topk_group": 4,
   "topk_method": "noaux_tc",
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.53.1",
-  "unsloth_fixed": true,
+  "transformers_version": "4.47.0",
   "use_cache": true,
   "v_head_dim": 128,
   "vocab_size": 129280