Update config.json

config.json

@@ -46,15 +46,25 @@
   "num_key_value_heads": 8,
   "num_local_experts": 32,
   "output_router_logits": false,
-  "pad_token_id": 200017,
+  "pad_token_id": 199999,
   "quantization_config": {
-    "modules_to_not_convert": [
-      "model.layers.*.self_attn",
-      "model.layers.*.mlp.router",
-      "model.embed_tokens",
-      "lm_head"
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": [
+      "router",
+      "lm_head",
+      "embed_tokens"
     ],
-    "quant_method": "mxfp4"
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
   },
   "rms_norm_eps": 1e-05,
   "rope_scaling": {
@@ -70,8 +80,8 @@
   "sliding_window": 128,
   "swiglu_limit": 7.0,
   "tie_word_embeddings": false,
+  "torch_dtype": "float16",
   "transformers_version": "4.55.0",
-  "unsloth_fixed": true,
   "use_cache": true,
   "vocab_size": 201088
 }