Main repository
https://github.com/martiansideofthemoon/rankgen
What is RankGen?
RankGen is a suite of encoder models (100M-1.2B parameters) which map prefixes and generations from any pretrained English language model to a shared vector space. RankGen can be used to rerank multiple full-length samples from an LM, and it can also be incorporated as a scoring function into beam search to significantly improve generation quality (0.85 vs 0.77 MAUVE, 75% preference according to humans annotators who are English writers).
Using RankGen
Loading RankGen is simple using the HuggingFace APIs (see Method-2 below), but we suggest using RankGenEncoder, which is a small wrapper around the HuggingFace APIs for correctly preprocessing data and doing tokenization automatically. You can either download the repository and install the API, or copy the implementation from below.
[SUGGESTED] Method-1: Loading the model with RankGenEncoder
from rankgen import RankGenEncoder, RankGenGenerator
rankgen_encoder = RankGenEncoder("kalpeshk2011/rankgen-t5-base-all")
# Encoding vectors
prefix_vectors = rankgen_encoder.encode(["This is a prefix sentence."], vectors_type="prefix")
suffix_vectors = rankgen_encoder.encode(["This is a suffix sentence."], vectors_type="suffix")
# Generating text
# use a HuggingFace compatible language model
generator = RankGenGenerator(rankgen_encoder=rankgen_encoder, language_model="gpt2-medium")
inputs = ["Whatever might be the nature of the tragedy it would be over with long before this, and those moving black spots away yonder to the west, that he had discerned from the bluff, were undoubtedly the departing raiders. There was nothing left for Keith to do except determine the fate of the unfortunates, and give their bodies decent burial. That any had escaped, or yet lived, was altogether unlikely, unless, perchance, women had been in the party, in which case they would have been borne away prisoners."]
# Baseline nucleus sampling
print(generator.generate_single(inputs, top_p=0.9)[0][0])
# Over-generate and re-rank
print(generator.overgenerate_rerank(inputs, top_p=0.9, num_samples=10)[0][0])
# Beam search
print(generator.beam_search(inputs, top_p=0.9, num_samples=10, beam_size=2)[0][0])
Method-2: Loading the model with HuggingFace APIs
from transformers import T5Tokenizer, AutoModel
tokenizer = T5Tokenizer.from_pretrained(f"google/t5-v1_1-base")
model = AutoModel.from_pretrained("kalpeshk2011/rankgen-t5-base-all", trust_remote_code=True)
RankGenEncoder Implementation
import tqdm
from transformers import T5Tokenizer, T5EncoderModel, AutoModel
class RankGenEncoder():
def __init__(self, model_path, max_batch_size=32, model_size=None, cache_dir=None):
assert model_path in ["kalpeshk2011/rankgen-t5-xl-all", "kalpeshk2011/rankgen-t5-xl-pg19", "kalpeshk2011/rankgen-t5-base-all", "kalpeshk2011/rankgen-t5-large-all"]
self.max_batch_size = max_batch_size
self.device = 'cuda' if torch.cuda.is_available() else 'cpu'
if model_size is None:
if "t5-large" in model_path or "t5_large" in model_path:
self.model_size = "large"
elif "t5-xl" in model_path or "t5_xl" in model_path:
self.model_size = "xl"
else:
self.model_size = "base"
else:
self.model_size = model_size
self.tokenizer = T5Tokenizer.from_pretrained(f"google/t5-v1_1-{self.model_size}", cache_dir=cache_dir)
self.model = AutoModel.from_pretrained(model_path, trust_remote_code=True)
self.model.to(self.device)
self.model.eval()
def encode(self, inputs, vectors_type="prefix", verbose=False, return_input_ids=False):
tokenizer = self.tokenizer
max_batch_size = self.max_batch_size
if isinstance(inputs, str):
inputs = [inputs]
if vectors_type == 'prefix':
inputs = ['pre ' + input for input in inputs]
max_length = 512
else:
inputs = ['suffi ' + input for input in inputs]
max_length = 128
all_embeddings = []
all_input_ids = []
for i in tqdm.tqdm(range(0, len(inputs), max_batch_size), total=(len(inputs) // max_batch_size) + 1, disable=not verbose, desc=f"Encoding {vectors_type} inputs:"):
tokenized_inputs = tokenizer(inputs[i:i + max_batch_size], return_tensors="pt", padding=True)
for k, v in tokenized_inputs.items():
tokenized_inputs[k] = v[:, :max_length]
tokenized_inputs = tokenized_inputs.to(self.device)
with torch.inference_mode():
batch_embeddings = self.model(**tokenized_inputs)
all_embeddings.append(batch_embeddings)
if return_input_ids:
all_input_ids.extend(tokenized_inputs.input_ids.cpu().tolist())
return {
"embeddings": torch.cat(all_embeddings, dim=0),
"input_ids": all_input_ids
}