intern13
/

DeepSeek-R1-Distill-Llama-8B-finetuned-q4

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

intern13 commited on 19 days ago

Commit

4d1f5ba

·

verified ·

1 Parent(s): 8f7ff7e

Upload model trained with Unsloth

Upload model trained with Unsloth 2x faster

Files changed (2) hide show

adapter_config.json +5 -5
adapter_model.safetensors +2 -2

adapter_config.json CHANGED Viewed

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "up_proj",
     "v_proj",
-    "k_proj",
-    "gate_proj",
-    "down_proj",
-    "o_proj",
-    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "q_proj",
     "up_proj",
     "v_proj",
+    "gate_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 sha256:60d95b10b6e140a9626a7058d5038528f2ff80148dc4569b881db56052046509
-size 40

 version https://git-lfs.github.com/spec/v1
+oid sha256:6f970f4d56786051ea1149f30a0105faa98a8188a2eb79fbce3f240f67444695
+size 167832240