File size: 1,873 Bytes
a2ea344
 
 
5e81d7f
 
 
 
 
 
a2ea344
 
5e81d7f
 
a2ea344
 
 
 
 
5e81d7f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
892dabf
5e81d7f
 
 
 
 
 
 
 
 
a2ea344
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
---
base_model: google/gemma-2b
library_name: peft
license: apache-2.0
datasets:
- jkhedri/psychology-dataset
language:
- en
pipeline_tag: question-answering
---
# Model Card for Model ID
A Gemma-2b finetuned LoRA trained on science Q&A
- **Developed by:** Venkat

<!-- Provide the basic links for the model. -->


## How to Get Started with the Model
```
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
from peft import PeftModel
from typing import Optional
import time
import os

def generate_prompt(input_text: str, instruction: Optional[str] = None) -> str:
    text = f"### Question: {input_text}\n\n### Answer: "
    if instruction:
        text = f"### Instruction: {instruction}\n\n{text}"
    return text

huggingface_token = os.environ.get('HUGGINGFACE_TOKEN')

base_model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", token=huggingface_token)
tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b", token=huggingface_token)

lora_model = PeftModel.from_pretrained(base_model, "vdpappu/lora_psychology-2")
merged_model = lora_model.merge_and_unload()

eos_token = '<eos>'
eos_token_id = tokenizer.encode(eos_token, add_special_tokens=False)[-1]

generation_config = GenerationConfig(
       eos_token_id=tokenizer.eos_token_id,
       min_length=5,
       max_length=200,
       do_sample=True,
       temperature=0.7,
       top_p=0.9,
       top_k=50,
       repetition_penalty=1.5,
       no_repeat_ngram_size=3,
       early_stopping=True
   )

question = "I feel lonely. What should I do?"
prompt = generate_prompt(input_text=question)

with torch.no_grad():
    inputs = tokenizer(prompt, return_tensors="pt")
    output = merged_model.generate(**inputs, generation_config=generation_config)
    response = tokenizer.decode(output[0], skip_special_tokens=True)

print(response)
```

- PEFT 0.12.0