neuralmagic
/

Llama-3.2-1B-Instruct-FP8

Text Generation

compressed-tensors

Model card Files Files and versions Community

mgoin commited on 1 day ago

Commit

5e302a2

•

1 Parent(s): 87c2def

Update config.json

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -6,7 +6,7 @@
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
-  "compression_config": {
     "config_groups": {
       "group_0": {
         "input_activations": {

   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
+  "quantization_config": {
     "config_groups": {
       "group_0": {
         "input_activations": {