unsloth
/

gemma-2b-bnb-4bit

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

danielhanchen commited on Feb 22

Commit

de74cc4

•

1 Parent(s): f8ec4db

Upload GemmaForCausalLM

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -17,7 +17,7 @@
   "num_attention_heads": 8,
   "num_hidden_layers": 18,
   "num_key_value_heads": 1,
-  "pad_token_id": 3,
   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,

   "num_attention_heads": 8,
   "num_hidden_layers": 18,
   "num_key_value_heads": 1,
+  "pad_token_id": 0,
   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,