Update config.json

config.json

@@ -94,39 +94,6 @@
     "q_lora_rank": 1536,
     "qk_nope_head_dim": 128,
     "qk_rope_head_dim": 64,
-    "quantization_config": {
-      "config_groups": {
-        "group_0": {
-          "input_activations": null,
-          "output_activations": null,
-          "targets": [
-            "Linear"
-          ],
-          "weights": {
-            "actorder": null,
-            "block_structure": null,
-            "dynamic": false,
-            "group_size": 32,
-            "num_bits": 4,
-            "observer": "minmax",
-            "observer_kwargs": {},
-            "strategy": "group",
-            "symmetric": true,
-            "type": "int"
-          }
-        }
-      },
-      "format": "pack-quantized",
-      "ignore": [
-        "lm_head",
-        "re:.*self_attn.*",
-        "re:.*shared_experts.*",
-        "re:.*mlp\\.(gate|up|gate_up|down)_proj.*"
-      ],
-      "kv_cache_scheme": null,
-      "quant_method": "compressed-tensors",
-      "quantization_status": "compressed"
-    },
     "remove_invalid_values": false,
     "repetition_penalty": 1.0,
     "return_dict": true,