phi-2-prompt-injection-QLoRA

README.md

@@ -7,18 +7,6 @@ base_model: microsoft/phi-2
 model-index:
 - name: phi-2-prompt-injection-QLoRA
   results: []
-datasets:
-- HuggingFaceH4/no_robots
-- Dahoas/synthetic-hh-rlhf-prompts
-- HuggingFaceH4/ultrachat_200k
-- Lakera/gandalf_ignore_instructions
-- imoxto/prompt_injection_cleaned_dataset-v2
-- hackaprompt/hackaprompt-dataset
-- rubend18/ChatGPT-Jailbreak-Prompts
-language:
-- en
-metrics:
-- accuracy
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -28,14 +16,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.0845
-- eval_precision: 0.9924
-- eval_recall: 0.9924
-- eval_f1-score: 0.9924
-- eval_accuracy: 0.9852
-- eval_runtime: 15.9089
-- eval_samples_per_second: 8.486
-- eval_steps_per_second: 1.069
+- eval_loss: 0.0000
+- eval_precision: 1.0
+- eval_recall: 1.0
+- eval_f1-score: 1.0
+- eval_accuracy: 1.0
+- eval_runtime: 16.0258
+- eval_samples_per_second: 8.424
+- eval_steps_per_second: 1.061
 - step: 0
 
 ## Model description
@@ -44,11 +32,7 @@ More information needed
 
 ## Intended uses & limitations
 
-```
-tokenizer = AutoTokenizer.from_pretrained("ysy970923/phi-2-prompt-injection-QLoRA")
-model = AutoModelForSequenceClassification.from_pretrained("ysy970923/phi-2-prompt-injection-QLoRA", load_in_4bit=True, torch_dtype=torch.bfloat16, id2label={0: "SAFE", 1: "INJECTION"})
-# LABEL_0 is safe, LABEL_1 is prompt_injection
-```
+More information needed
 
 ## Training and evaluation data
 

adapter_config.json

@@ -20,8 +20,8 @@
   "revision": null,
   "target_modules": [
     "v_proj",
-    "k_proj",
-    "q_proj"
+    "q_proj",
+    "k_proj"
   ],
   "task_type": "SEQ_CLS",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:516e58b719f01c6cbf482e86ceeae52e4edeeeb7097da527c5f21c7c87036c54
+oid sha256:f3b18b734addf17df5b076584597070234de62592558854002b9a6ec228f79a2
 size 31503624

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38944c8d9f5c1431db7e99cddb755dce36b31106a2e870c3d6f86d547e0c82c9
+oid sha256:2e695bc3cf97c9e7b12dacee1b4b7f442e03d12888c4f127e5ade30c3e997e3a
 size 4856