File size: 1,575 Bytes
9d2fb6e 86b178b 9d2fb6e 86b178b 9d2fb6e 86b178b 9d2fb6e 86b178b 9d2fb6e 86b178b 9d2fb6e 86b178b 9d2fb6e 86b178b 9d2fb6e |
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 |
---
tags:
- autotrain
- text-generation
widget:
- text: 'I love AutoTrain because '
license: apache-2.0
datasets:
- manjunathshiva/autotrain-data-GRADE3B-7B-02
language:
- en
---
# Model Trained Using AutoTrain
This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
# Usage
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch
access_token = "<HF_TOKEN>"
tokenizer = AutoTokenizer.from_pretrained(
"meta-llama/Llama-2-7b-chat-hf"
)
base_model = AutoModelForCausalLM.from_pretrained(
'meta-llama/Llama-2-7b-chat-hf',
token=access_token,
trust_remote_code=True,
#device_map="auto", #Uncomment if you hava a good GPU Memory
torch_dtype=torch.float16,
offload_folder="offload/"
)
model = PeftModel.from_pretrained(
base_model,
'manjunathshiva/GRADE3B-7B-02-0',
token=access_token,
offload_folder="offload/"
).eval()
# Prompt content: "When is Maths Unit Test 2?"
messages = [
{"role": "user", "content": "When is Maths Unit Test 2?"}
]
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
#output_ids = model.generate(input_ids.to('cuda')) #Uncomment if you have CUDA and comment below line
output_ids = model.generate(input_ids=input_ids, temperature=0.01 )
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
# Model response: "<Outputs Date>"
print(response)
``` |