|
--- |
|
tags: |
|
- flan |
|
- opt |
|
- peft |
|
datasets: |
|
- SirNeural/flan_v2 |
|
metrics: |
|
- perplexity |
|
base_model: facebook/opt-2.7b |
|
--- |
|
|
|
## FLAN-OPT-2.7b-LoRA |
|
|
|
OPT was first introduced in [Open Pre-trained Transformer Language Models](https://arxiv.org/abs/2205.01068) and first released in [metaseq's repository](https://github.com/facebookresearch/metaseq) on May 3rd 2022 by Meta AI. |
|
|
|
This model is [facebook/opt-2.7b](https://hf.co/facebook/opt-2.7b) finetuned with low-rank adapters (https://arxiv.org/abs/2106.09685) on the FLAN datasets (https://arxiv.org/pdf/2210.11416.pdf). |
|
|
|
Low-rank adapters (r=16) finetuned over 1.1m new tokens of a FLAN task mixture, with the start of each example cut off if it was too large to fit within a 256 token context. |
|
|
|
The model reaches a train ppl of 5.09 and an eval ppl of 4.36. |
|
|
|
### Inference Example (Chain-of-Thought prompt): |
|
|
|
```python |
|
# %pip install -qq transformers git+https://github.com/huggingface/peft accelerate bitsandbytes |
|
from peft import PeftModel, PeftConfig |
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
peft_model_id = "crumb/FLAN-OPT-2.7b-LoRA" |
|
|
|
config = PeftConfig.from_pretrained(peft_model_id) |
|
model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path, load_in_8bit=True, low_cpu_mem_usage=True, device_map='auto') |
|
model = PeftModel.from_pretrained(model, peft_model_id) |
|
tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path) |
|
|
|
import torch |
|
prompt = """ |
|
Q: Answer the following yes/no question by reasoning step-by-step. Could a dandelion suffer from hepatitis? |
|
A: Hepatitis only affects organisms with livers. Dandelions don’t have a liver. The answer is no. |
|
|
|
Q: Answer the following yes/no question by reasoning step-by-step. Can you write a whole Haiku in a single tweet? |
|
A: A haiku is a japanese three-line poem. That is short enough to fit in 280 characters. The answer is yes. |
|
|
|
Q: Answer the following yes/no question by reasoning step-by-step. Can you reach space with a Cessna? |
|
A: |
|
""".strip() |
|
inputs = tokenizer([prompt], return_tensors='pt') |
|
|
|
with torch.autocast("cuda", dtype=torch.float16): |
|
outputs = model.generate( |
|
input_ids=inputs.input_ids.cuda(), |
|
attention_mask=inputs.attention_mask.cuda(), |
|
max_new_tokens=32, |
|
top_k=4, |
|
penalty_alpha=0.6 |
|
) |
|
print("\n".join(tokenizer.decode(outputs[0]).split("\n")[:prompt.count("\n")+1])) |
|
# Cessna is a single-engine aircraft. Cessna cannot reach space. The answer is no. |
|
``` |
