Update config.json

config.json中vocab_size （154880）, 与 tokenizer.json中实际的token数量（154856）不一致？导致eagle推理解码出超过154855的token_id（154879）然后不被接收，vocab_size这里是否应该改为154856？
![企业微信截图_17732146513158](https://cdn-uploads.huggingface.co/production/uploads/64872e75a37e73308ecabca4/l6219x7eouKb-y79fYeop.png)

![企业微信截图_17732146299820](https://cdn-uploads.huggingface.co/production/uploads/64872e75a37e73308ecabca4/EhEwbnYQXXQx3_-SXKB9_.png)

![企业微信截图_17732114034124](https://cdn-uploads.huggingface.co/production/uploads/64872e75a37e73308ecabca4/Y_tObRfCjQtwk5Co-Hins.png)

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -55,7 +55,7 @@
   "transformers_version": "5.0.2.dev0",
   "use_cache": true,
   "v_head_dim": 256,
-  "vocab_size": 154880,
   "quantization_config": {
     "activation_scheme": "dynamic",
     "fmt": "e4m3",

   "transformers_version": "5.0.2.dev0",
   "use_cache": true,
   "v_head_dim": 256,
+  "vocab_size": 154856,
   "quantization_config": {
     "activation_scheme": "dynamic",
     "fmt": "e4m3",