from angle_emb import AnglE, Prompts

angle = AnglE.from_pretrained('WhereIsAI/UAE-Large-V1', pooling_strategy='cls').cuda()
angle.set_prompt(prompt=Prompts.C)
vec = angle.encode({'text': 'hello world'}, to_numpy=True)
print(vec)
vecs = angle.encode([{'text': 'hello world1'}, {'text': 'hello world2'}], to_numpy=True)
print(vecs)

from angle_emb import AnglE

angle = AnglE.from_pretrained('WhereIsAI/UAE-Large-V1', pooling_strategy='cls').cuda()
vec = angle.encode('hello world', to_numpy=True)
print(vec)
vecs = angle.encode(['hello world1', 'hello world2'], to_numpy=True)
print(vecs)

from angle_emb import AnglE, Prompts

angle = AnglE.from_pretrained('NousResearch/Llama-2-7b-hf', pretrained_lora_path='SeanLee97/angle-llama-7b-nli-v2')

print('All predefined prompts:', Prompts.list_prompts())
angle.set_prompt(prompt=Prompts.A)
print('prompt:', angle.prompt)
vec = angle.encode({'text': 'hello world'}, to_numpy=True)
print(vec)
vecs = angle.encode([{'text': 'hello world1'}, {'text': 'hello world2'}], to_numpy=True)
print(vecs)

from angle_emb import AnglE
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel, PeftConfig

peft_model_id = 'SeanLee97/angle-llama-7b-nli-v2'
config = PeftConfig.from_pretrained(peft_model_id)
tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path).bfloat16().cuda()
model = PeftModel.from_pretrained(model, peft_model_id).cuda()

def decorate_text(text: str):
    return Prompts.A.format(text=text)

inputs = 'hello world!'
tok = tokenizer([decorate_text(inputs)], return_tensors='pt')
for k, v in tok.items():
    tok[k] = v.cuda()
vec = model(output_hidden_states=True, **tok).hidden_states[-1][:, -1].float().detach().cpu().numpy()
print(vec)

from angle_emb import AnglE

angle = AnglE.from_pretrained('SeanLee97/angle-bert-base-uncased-nli-en-v1', pooling_strategy='cls_avg').cuda()
vec = angle.encode('hello world', to_numpy=True)
print(vec)
vecs = angle.encode(['hello world1', 'hello world2'], to_numpy=True)
print(vecs)

import torch
from transformers import AutoModel, AutoTokenizer

model_id = 'SeanLee97/angle-bert-base-uncased-nli-en-v1'
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModel.from_pretrained(model_id).cuda()

inputs = 'hello world!'
tok = tokenizer([inputs], return_tensors='pt')
for k, v in tok.items():
    tok[k] = v.cuda()
hidden_state = model(**tok).last_hidden_state
vec = (hidden_state[:, 0] + torch.mean(hidden_state, dim=1)) / 2.0
print(vec)

from datasets import load_dataset
from angle_emb import AnglE, AngleDataTokenizer


# 1. load pretrained model
angle = AnglE.from_pretrained('SeanLee97/angle-bert-base-uncased-nli-en-v1', max_length=128, pooling_strategy='cls').cuda()

# 2. load dataset
# `text1`, `text2`, and `label` are three required columns.
ds = load_dataset('mteb/stsbenchmark-sts')
ds = ds.map(lambda obj: {"text1": str(obj["sentence1"]), "text2": str(obj['sentence2']), "label": obj['score']})
ds = ds.select_columns(["text1", "text2", "label"])

# 3. transform data
train_ds = ds['train'].shuffle().map(AngleDataTokenizer(angle.tokenizer, angle.max_length), num_proc=8)
valid_ds = ds['validation'].map(AngleDataTokenizer(angle.tokenizer, angle.max_length), num_proc=8)
test_ds = ds['test'].map(AngleDataTokenizer(angle.tokenizer, angle.max_length), num_proc=8)

# 4. fit
angle.fit(
    train_ds=train_ds,
    valid_ds=valid_ds,
    output_dir='ckpts/sts-b',
    batch_size=32,
    epochs=5,
    learning_rate=2e-5,
    save_steps=100,
    eval_steps=1000,
    warmup_steps=0,
    gradient_accumulation_steps=1,
    loss_kwargs={
        'w1': 1.0,
        'w2': 1.0,
        'w3': 1.0,
        'cosine_tau': 20,
        'ibn_tau': 20,
        'angle_tau': 1.0
    },
    fp16=True,
    logging_steps=100
)

# 5. evaluate
corrcoef, accuracy = angle.evaluate(test_ds, device=angle.device)
print('corrcoef:', corrcoef)