relaxml
/

Llama-2-70b-chat-E8PRVQ-4Bit

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Update config.json

#3

by AnantShyamMathML - opened Jul 3

base: refs/heads/main

←

from: refs/pr/3

Discussion Files changed

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -17,7 +17,7 @@
   "num_hidden_layers": 80,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
-  "quip_params": {
     "codebook": "E8P12RVQ4B",
     "codebook_version": 1,
     "codesz": 8,

   "num_hidden_layers": 80,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
+  "quantization_config": {
     "codebook": "E8P12RVQ4B",
     "codebook_version": 1,
     "codesz": 8,