darkB commited on
Commit
0cdf1a3
·
verified ·
1 Parent(s): 8f0af1a

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +32 -0
README.md ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # PEFT Adapter for Quantum Computing QA
2
+
3
+ PEFT adapter for Quantum Computing QA
4
+
5
+ ## Model Description
6
+
7
+ This is a PEFT adapter trained for quantum computing question-answering tasks.
8
+
9
+ - **Base Model**: mistralai/Mistral-7B-Instruct-v0.3
10
+ - **Training Method**: LoRA
11
+ - **Task**: Question Answering
12
+ - **Domain**: Quantum Computing
13
+
14
+ ## Usage
15
+
16
+ ```python
17
+ from peft import PeftModel, PeftConfig
18
+ from transformers import AutoModelForCausalLM, AutoTokenizer
19
+
20
+ # Load base model
21
+ base_model = AutoModelForCausalLM.from_pretrained(
22
+ "mistralai/Mistral-7B-Instruct-v0.3",
23
+ device_map="auto",
24
+ trust_remote_code=True
25
+ )
26
+
27
+ # Load adapter
28
+ model = PeftModel.from_pretrained(
29
+ base_model,
30
+ "darkB/quantum-qa-test-adapter"
31
+ )
32
+ ```