Zangs3011
/

quantize_push

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions

Zangs3011 commited on Apr 23, 2024

Commit

21c7533

·

verified ·

1 Parent(s): 33cd8cc

Upload model

Files changed (2) hide show

adapter_config.json +3 -3
adapter_model.safetensors +2 -2

adapter_config.json CHANGED Viewed

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "facebook/opt-1.3b",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -21,9 +21,9 @@
   "revision": null,
   "target_modules": [
     "q_proj",
-    "k_proj",
     "o_proj",
-    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

 {
   "alpha_pattern": {},
   "auto_mapping": null,
+  "base_model_name_or_path": "facebook/opt-125m",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
   "revision": null,
   "target_modules": [
     "q_proj",
     "o_proj",
+    "v_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57d525ebcc549ad6324bfeeec0e31cb26f9b893205716b2719bc669b9e134fdf
-size 4738808

 version https://git-lfs.github.com/spec/v1
+oid sha256:13eded0c91405be45dc94d3fc3a6785fc35bbb919bfbce80fce7e77ee6fe4483
+size 894632