File size: 2,736 Bytes
2d16aef a20177a 2d16aef c89c483 |
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 |
---
library_name: peft
base_model: meta-llama/Llama-2-7b-hf
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.4.0
notebook (training and inference): https://colab.research.google.com/drive/1GxbUYZiLidteVX4qu5iSox6oxxEOHk5O?usp=sharing
Usage:
```python
import requests
# Get a random Wikipedia article summary using their API
def random_extract():
URL = "https://en.wikipedia.org/api/rest_v1/page/random/summary"
PARAMS = {}
r = requests.get(url = URL, params = PARAMS)
data = r.json()
return data['extract']
# Format this as a prompt that would hopefully result in the model completing with a question
def random_prompt():
e = random_extract()
return f"""### CONTEXT: {e} ### QUESTION:"""
import torch
from peft import AutoPeftModelForCausalLM
from transformers import AutoTokenizer
output_dir = "mcqgen_test"
# load base LLM model and tokenizer
model = AutoPeftModelForCausalLM.from_pretrained(
output_dir,
low_cpu_mem_usage=True,
torch_dtype=torch.float16,
load_in_4bit=True,
)
tokenizer = AutoTokenizer.from_pretrained(output_dir)
# We can feed in a random context prompt and see what question the model comes up with:
prompt = random_prompt()
input_ids = tokenizer(prompt, return_tensors="pt", truncation=True).input_ids.cuda()
# with torch.inference_mode():
outputs = model.generate(input_ids=input_ids, max_new_tokens=100, do_sample=True, top_p=0.9,temperature=0.9)
print(f"Prompt:\n{prompt}\n")
print(f"Generated MCQ:\n### QUESTION:{tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True)[0][len(prompt):]}")
def process_outputs(outputs):
s = tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True)[0]
split = s.split("### ")[1:][:7]
if len(split) != 7:
return None
# Check the starts
expected_starts = ['CONTEXT', 'QUESTION', 'A' , 'B', 'C', 'D', 'CORRECT']
for i, s in enumerate(split):
if not split[i].startswith(expected_starts[i]):
return None
return {
"context": split[0].replace("CONTEXT: ", ""),
"question": split[1].replace("QUESTION: ", ""),
"a": split[2].replace("A: ", ""),
"b": split[3].replace("B: ", ""),
"c": split[4].replace("C: ", ""),
"d": split[5].replace("D: ", ""),
"correct": split[6].replace("CORRECT: ", "")
}
process_outputs(outputs) # A nice dictionary hopefully
``` |