Update README.md
Browse files
README.md
CHANGED
@@ -38,18 +38,18 @@ For example, to chat with the finance model:
|
|
38 |
```python
|
39 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
40 |
|
41 |
-
model = AutoModelForCausalLM.from_pretrained("AdaptLLM/
|
42 |
-
tokenizer = AutoTokenizer.from_pretrained("AdaptLLM/
|
43 |
|
44 |
# Put your input here:
|
45 |
-
user_input = '''
|
46 |
-
|
47 |
-
|
48 |
-
|
49 |
-
|
50 |
-
|
51 |
|
52 |
-
|
53 |
|
54 |
# We use the prompt template of LLaMA-2-Chat demo
|
55 |
prompt = f"<s>[INST] <<SYS>>\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\n\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\n<</SYS>>\n\n{user_input} [/INST]"
|
@@ -62,6 +62,7 @@ pred = tokenizer.decode(outputs[answer_start:], skip_special_tokens=True)
|
|
62 |
|
63 |
print(f'### User Input:\n{user_input}\n\n### Assistant Output:\n{pred}')
|
64 |
```
|
|
|
65 |
## Domain-Specific Tasks
|
66 |
To easily reproduce our results, we have uploaded the filled-in zero/few-shot input instructions and output completions of each domain-specific task: [biomedicine-tasks](https://huggingface.co/datasets/AdaptLLM/medicine-tasks), [finance-tasks](https://huggingface.co/datasets/AdaptLLM/finance-tasks), and [law-tasks](https://huggingface.co/datasets/AdaptLLM/law-tasks).
|
67 |
|
|
|
38 |
```python
|
39 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
40 |
|
41 |
+
model = AutoModelForCausalLM.from_pretrained("AdaptLLM/medicine-chat")
|
42 |
+
tokenizer = AutoTokenizer.from_pretrained("AdaptLLM/medicine-chat", use_fast=False)
|
43 |
|
44 |
# Put your input here:
|
45 |
+
user_input = '''Question: Which of the following is an example of monosomy?
|
46 |
+
Options:
|
47 |
+
- 46,XX
|
48 |
+
- 47,XXX
|
49 |
+
- 69,XYY
|
50 |
+
- 45,X
|
51 |
|
52 |
+
Please provide your choice first and then provide explanations if possible.'''
|
53 |
|
54 |
# We use the prompt template of LLaMA-2-Chat demo
|
55 |
prompt = f"<s>[INST] <<SYS>>\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\n\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\n<</SYS>>\n\n{user_input} [/INST]"
|
|
|
62 |
|
63 |
print(f'### User Input:\n{user_input}\n\n### Assistant Output:\n{pred}')
|
64 |
```
|
65 |
+
|
66 |
## Domain-Specific Tasks
|
67 |
To easily reproduce our results, we have uploaded the filled-in zero/few-shot input instructions and output completions of each domain-specific task: [biomedicine-tasks](https://huggingface.co/datasets/AdaptLLM/medicine-tasks), [finance-tasks](https://huggingface.co/datasets/AdaptLLM/finance-tasks), and [law-tasks](https://huggingface.co/datasets/AdaptLLM/law-tasks).
|
68 |
|