herrkobold
/

SauerkrautLM-gemma-2-2b-it-bnb-4bit

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

herrkobold commited on 29 days ago

Commit

b0d0a84

•

1 Parent(s): f90bcec

Upload Gemma2ForCausalLM

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -28,7 +28,7 @@
   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "float32",
     "bnb_4bit_quant_storage": "uint8",
     "bnb_4bit_quant_type": "fp4",
     "bnb_4bit_use_double_quant": false,

   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
     "bnb_4bit_quant_storage": "uint8",
     "bnb_4bit_quant_type": "fp4",
     "bnb_4bit_use_double_quant": false,