adriata
/

med_mistral_4bit

Text Generation

Inference Endpoints

text-generation-inference

4-bit precision

Model card Files Files and versions Community

adriata commited on Feb 25

Commit

2e2be22

•

1 Parent(s): 7996466

Update config.json

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -15,7 +15,7 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
-  "pad_token_id": "<unk>",
   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,

   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
+  "pad_token_id": 2,
   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,