Proper bos_token_id

README.md

@@ -8,6 +8,8 @@ tags:
 - mergekitty
 - merge
 ---
+# UPDATE: 07.06.2025
+- Proper bos_token_id was uploaded. Download the new config.json file for the model to work properly!
 ## Quantized using the default exllamav3 (0.0.2) quantization process.
 
 - Original model: https://huggingface.co/trashpanda-org/QwQ-32B-Snowdrop-v0

config.json

@@ -5,7 +5,7 @@
     ],
     "attention_dropout": 0.0,
     "bos_token_id": 151643,
-    "eos_token_id": 151643,
+    "eos_token_id": 151645,
     "hidden_act": "silu",
     "hidden_size": 5120,
     "initializer_range": 0.02,
@@ -28,9 +28,9 @@
     "vocab_size": 151665,
     "quantization_config": {
         "quant_method": "exl3",
-        "version": "0.0.2",
-        "bits": 4.5,
-        "head_bits": 8,
+        "version": "0.0.1",
+        "bits": 4.0,
+        "head_bits": 6,
         "calibration": {
             "rows": 100,
             "cols": 2048