Adding `safetensors` variant of this model

README.md

@@ -5,19 +5,46 @@ language:
 tags:
   - generation
 license: apache-2.0
----
-
-Pretrained GPT2 with expanded n_ctx up to 2048(also with expanded embedding dimension to 1536) in Korean.
-# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
-Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_psyche__kogpt)
+model-index:
+  - name: task_1
+    results:
+      - task:
+          type: natural-language-generation
+        dataset:
+          type: hellaswag
+          name: hellaswag(10 shots)
+        metrics:
+          - type: acc_norm
+            value: 27.7
+  - name: task_2
+    results:
+      - task:
+          type: natural-language-generation
+        dataset:
+          type: ARC
+          name: ARC(25 shots)
+        metrics:
+          - type: acc_norm
+            value: 23.8
+  - name: task_3
+    results:
+      - task:
+          type: natural-language-generation
+        dataset:
+          type: MMLU
+          name: MMLU(5 shots)
+        metrics:
+          - type: acc
+            value: 24.9
 
-| Metric                | Value                     |
-|-----------------------|---------------------------|
-| Avg.                  | 24.27   |
-| ARC (25-shot)         | 21.16          |
-| HellaSwag (10-shot)   | 28.11    |
-| MMLU (5-shot)         | 26.56         |
-| TruthfulQA (0-shot)   | 42.06   |
-| Winogrande (5-shot)   | 49.09   |
-| GSM8K (5-shot)        | 0.0        |
-| DROP (3-shot)         | 2.89         |
+  - name: task_4
+    results:
+      - task:
+          type: natural-language-generation
+        dataset:
+          type: TruthfulQA 
+          name: TruthfulQA(0 shots)
+        metrics:
+          - type: mc2
+            value: 46.5
+---

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "psyche/kogpt",
+  "_name_or_path": "runs/checkpoint-47500",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -33,7 +33,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.31.0",
+  "transformers_version": "4.30.2",
   "use_cache": true,
   "vocab_size": 32002
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 0,
   "eos_token_id": 2,
-  "transformers_version": "4.31.0"
+  "transformers_version": "4.30.2"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bb7be5d1b9b55633082dd466d75a8f6028b02bfa2255a430cdb6b63a3ac1e6d
-size 1569174365
+oid sha256:6174fe3c21d632e922a498fd5d347893add6efd757af0c3f7c316d9e78040346
+size 891699345

rust_model.ot

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e80d7e388967e4b2a2cb00047bc0cc7751fbe6249dd09a18f5e16bee8e62db61
+size 1817336536