File size: 2,454 Bytes
16cfed1 5242895 |
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 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 |
---
license: other
---
# Hugging Face Model - Bengali Finetuned
This repository contains a Hugging Face model that has been fine-tuned on a Bengali dataset. The model uses the `peft` library for generating responses.
## Usage
To use the model, first import the necessary libraries:
```python
from peft import PeftModel
from transformers import LlamaTokenizer, LlamaForCausalLM, GenerationConfig
```
Next, load the tokenizer and model:
```python
tokenizer = LlamaTokenizer.from_pretrained("yahma/llama-7b-hf")
model = LlamaForCausalLM.from_pretrained(
"yahma/llama-7b-hf",
load_in_8bit=True,
device_map="auto",
)
```
Then, load the `PeftModel` with the specified pre-trained model and path to the peft model:
```python
model = PeftModel.from_pretrained(model, "./bengali-dolly-alpaca-lora-7b")
```
Next, define a function to generate a prompt:
```python
def generate_prompt(instruction, input=None):
if input:
return f"""Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
### Instruction:
{instruction}
### Input:
{input}
### Response:"""
else:
return f"""Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{instruction}
### Response:"""
```
Finally, define a function to evaluate the model:
```python
generation_config = GenerationConfig(
temperature=0.1,
top_p=0.75,
num_beams=4,
)
def evaluate(model, instruction, input=None):
prompt = generate_prompt(instruction, input)
inputs = tokenizer(prompt, return_tensors="pt")
input_ids = inputs["input_ids"].cuda()
generation_output = model.generate(
input_ids=input_ids,
generation_config=generation_config,
return_dict_in_generate=True,
output_scores=True,
max_new_tokens=256
)
for s in generation_output.sequences:
output = tokenizer.decode(s)
print("Response:", output.split("### Response:")[1].strip())
instruct =input("Instruction: ")
evaluate(model, instruct)
```
To generate a response, simply run the `evaluate` function with an instruction and optional input:
```python
instruct = "Write a response that appropriately completes the request."
input = "This is a sample input."
evaluate(model, instruct, input)
```
This will output a response that completes the request.
|