Upload model

README.md

@@ -1,34 +1,8 @@
 ---
 library_name: peft
-base_model: KT-AI/midm-bitext-S-7B-inst-v1
+base_model: meta-llama/Llama-2-7b-chat-hf
 ---
-# Accuracy
-## 결과 분석
 
-### 상위 1000개의 test dataset을 이용해 성능 확인
-
-|               | TP    | TN   |
-|:-------------:|:-----:|:----:|
-| FP            | 452   | 41   | 
-| FN            | 43    | 440  |
-
-
-
-
-- **True Positive**: 452
-- **True Negative**: 440
-- **False Positive**: 41
-- **False Negative**: 43
-  
-- **precision**: 0.9168356997971603
-- **recall**: 0.9131313131313131
-- **f1 score**: 0.9149797570850203
-
-
-#### '긍정'과 '부정'에 포함되지 않은 단어로 예측한 경우
-
-- **' ', '정'으로 예측**: 총 24개
-  
 # Model Card for Model ID
 
 <!-- Provide a quick summary of what the model is/does. -->
@@ -242,4 +216,5 @@ The following `bitsandbytes` quantization config was used during training:
 
 ### Framework versions
 
-- PEFT 0.6.2
+
+- PEFT 0.6.2

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "KT-AI/midm-bitext-S-7B-inst-v1",
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -16,9 +16,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "c_proj",
-    "c_attn",
-    "c_fc"
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec191b81e42cdc67a1cf6e8f8f62dae1321ac27fbaa0141fd09ea57aaa710482
-size 67010784
+oid sha256:f547d951b79226b6bd479eb5bcf6f89635bac809ec585f573faf84400bd3de8f
+size 80013120