Upload config.json with huggingface_hub

config.json

@@ -4,8 +4,6 @@
   ],
   "attention_bias": true,
   "attention_dropout": 0.0,
-  "bos_token_id": null,
-  "dtype": "bfloat16",
   "eos_token_id": 200002,
   "experts_per_token": 4,
   "head_dim": 64,
@@ -61,21 +59,30 @@
   "num_local_experts": 128,
   "output_router_logits": false,
   "pad_token_id": 199999,
+  "quantization_config": {
+    "modules_to_not_convert": [
+      "model.layers.*.self_attn",
+      "model.layers.*.mlp.router",
+      "model.embed_tokens",
+      "lm_head"
+    ],
+    "quant_method": "mxfp4"
+  },
   "rms_norm_eps": 1e-05,
-  "rope_parameters": {
+  "rope_scaling": {
     "beta_fast": 32.0,
     "beta_slow": 1.0,
     "factor": 32.0,
     "original_max_position_embeddings": 4096,
-    "rope_theta": 150000,
     "rope_type": "yarn",
     "truncate": false
   },
+  "rope_theta": 150000,
   "router_aux_loss_coef": 0.9,
   "sliding_window": 128,
   "swiglu_limit": 7.0,
   "tie_word_embeddings": false,
-  "transformers_version": "5.1.0",
+  "transformers_version": "4.55.0.dev0",
   "use_cache": true,
   "vocab_size": 201088
 }