prem-research
/

MiniGuard-v0.1-GPTQ-4bit

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions

ojus1 commited on Jan 10

Commit

62e3adb

·

verified ·

1 Parent(s): aacc2ce

Upload Qwen3ForCausalLM

Files changed (2) hide show

config.json +1 -1
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -51,7 +51,7 @@
   "quantization_config": {
     "backend": "auto",
     "batch_size": 1,
-    "bits": 8,
     "block_name_to_quantize": null,
     "cache_block_outputs": true,
     "checkpoint_format": "gptq",

   "quantization_config": {
     "backend": "auto",
     "batch_size": 1,
+    "bits": 4,
     "block_name_to_quantize": null,
     "cache_block_outputs": true,
     "checkpoint_format": "gptq",

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3abd4b87e74fdd491df555988347333e845214e9e4d732035ed44d64a3bf15f3
-size 763265296

 version https://git-lfs.github.com/spec/v1
+oid sha256:bd060502a112936933da972eb6547d59b3361bb7a49a6b29901e8f022c11af4e
+size 541343728