Add library name

#1
by nielsr HF Staff - opened
Files changed (1) hide show
  1. README.md +19 -6
README.md CHANGED
@@ -1,9 +1,9 @@
1
  ---
2
- license: apache-2.0
 
3
  language:
4
  - en
5
- base_model:
6
- - Qwen/Qwen2.5-7B-Instruct
7
  pipeline_tag: question-answering
8
  tags:
9
  - medical
@@ -11,6 +11,7 @@ tags:
11
  - lora
12
  - dpo
13
  - reflection
 
14
  ---
15
 
16
  <div align="center">
@@ -67,8 +68,17 @@ base_model = AutoModelForCausalLM.from_pretrained(
67
  model = PeftModel.from_pretrained(base_model, lora_path)
68
 
69
  # Prepare the prompt
70
- system_prompt = '''You are a helpful medical expert specializing in USMLE exam questions, and your task is to answer a multi-choice medical question. Please first think step-by-step and then choose the answer from the provided options. Your responses will be used for research purposes only, so please have a definite answer.\nProvide your response in the following JSON format:\n{"reason": "Step-by-step explanation of your thought process","answer": "Chosen answer from the given options"}\n'''
71
- user_prompt = "A 67-year-old man with transitional cell carcinoma of the bladder comes to the physician because of a 2-day history of ringing sensation in his ear. He received this first course of neoadjuvant chemotherapy 1 week ago. Pure tone audiometry shows a sensorineural hearing loss of 45 dB. The expected beneficial effect of the drug that caused this patient's symptoms is most likely due to which of the following actions?\nOptions:\nA: Inhibition of thymidine synthesis\nB: Inhibition of proteasome\nC: Hyperstabilization of microtubules\nD: Generation of free radicals\nE: Cross-linking of DNA"
 
 
 
 
 
 
 
 
 
72
 
73
  messages = [
74
  {"role": "system", "content": system_prompt},
@@ -101,5 +111,8 @@ print(tokenizer.decode(response, skip_special_tokens=True))
101
  If you use these weights or the Med-REFL framework in your research, please cite our paper:
102
  ```
103
 
 
 
 
104
 
105
- ```
 
1
  ---
2
+ base_model:
3
+ - Qwen/Qwen2.5-7B-Instruct
4
  language:
5
  - en
6
+ license: apache-2.0
 
7
  pipeline_tag: question-answering
8
  tags:
9
  - medical
 
11
  - lora
12
  - dpo
13
  - reflection
14
+ library_name: transformers
15
  ---
16
 
17
  <div align="center">
 
68
  model = PeftModel.from_pretrained(base_model, lora_path)
69
 
70
  # Prepare the prompt
71
+ system_prompt = '''You are a helpful medical expert specializing in USMLE exam questions, and your task is to answer a multi-choice medical question. Please first think step-by-step and then choose the answer from the provided options. Your responses will be used for research purposes only, so please have a definite answer.
72
+ Provide your response in the following JSON format:
73
+ {"reason": "Step-by-step explanation of your thought process","answer": "Chosen answer from the given options"}
74
+ '''
75
+ user_prompt = "A 67-year-old man with transitional cell carcinoma of the bladder comes to the physician because of a 2-day history of ringing sensation in his ear. He received this first course of neoadjuvant chemotherapy 1 week ago. Pure tone audiometry shows a sensorineural hearing loss of 45 dB. The expected beneficial effect of the drug that caused this patient's symptoms is most likely due to which of the following actions?
76
+ Options:
77
+ A: Inhibition of thymidine synthesis
78
+ B: Inhibition of proteasome
79
+ C: Hyperstabilization of microtubules
80
+ D: Generation of free radicals
81
+ E: Cross-linking of DNA"
82
 
83
  messages = [
84
  {"role": "system", "content": system_prompt},
 
111
  If you use these weights or the Med-REFL framework in your research, please cite our paper:
112
  ```
113
 
114
+ ```
115
+
116
+ ## Star History
117
 
118
+ [![Star History Chart](https://api.star-history.com/svg?repos=TianYin123/Med-REFL&type=Date)](https://www.star-history.com/#TianYin123/Med-REFL&Date)