import llm_blender
blender = llm_blender.Blender()
blender.loadranker("llm-blender/PairRM") # load ranker checkpoint

inputs = ["hello, how are you!", "I love you!"]
candidates_texts = [["get out!", "hi! I am fine, thanks!", "bye!"], 
                    ["I love you too!", "I hate you!", "Thanks! You're a good guy!"]]
ranks = blender.rank(inputs, candidates_texts, return_scores=False, batch_size=1)
# ranks is a list of ranks where ranks[i][j] represents the ranks of candidate-j for input-i
"""
ranks -->
array([[3, 1, 2], # it means "hi! I am fine, thanks!" ranks the 1st, "bye" ranks the 2nd, and "get out!" ranks the 3rd. 
       [1, 3, 2]], # it means "I love you too"! ranks the the 1st, and "I hate you!" ranks the 3rd.
       dtype=int32) 

"""

inputs = ["hello!", "I love you!"]
candidates_A = ["hi!", "I hate you!"]
candidates_B = ["f**k off!", "I love you, too!"]
comparison_results = blender.compare(inputs, candidates_A, candidates_B)
# comparison_results is a list of bool, where comparison_results[i] denotes whether candidates_A[i] is better than candidates_B[i] for inputs[i]
# comparison_results[0]--> True 

blender.loadfuser("llm-blender/gen_fuser_3b") # load fuser checkpoint if you want to use pre-trained fuser; or you can use ranker only
from llm_blender.blender.blender_utils import get_topk_candidates_from_ranks
topk_candidates = get_topk_candidates_from_ranks(ranks, candidates_texts, top_k=3)
fuse_generations = blender.fuse(inputs, topk_candidates, batch_size=2)
# fuse_generations are the fused generations from our fine-tuned checkpoint

# You can also do the rank and fusion with a single function

fuse_generations, ranks = blender.rank_and_fuse(inputs, candidates_texts, return_scores=False, batch_size=2, top_k=3)

import llm_blender
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("HuggingFaceH4/zephyr-7b-beta")
model = AutoModelForCausalLM.from_pretrained("HuggingFaceH4/zephyr-7b-beta", device_map="auto")
system_message = {"role": "system", "content": "You are a friendly chatbot."}

inputs = ["can you tell me a joke about OpenAI?"]
messages = [[system_message, {"role": "user", "content": _input}] for _input in inputs]
prompts = [tokenizer.apply_chat_template(m, tokenize=False, add_generation_prompt=True) for m in messages]

# standard sampling generation 
input_ids = tokenizer(prompts[0], return_tensors="pt").input_ids
sampled_outputs = model.generate(input_ids, do_sample=True, top_k=50, top_p=0.95, num_return_sequences=1)
print(tokenizer.decode(sampled_outputs[0][len(input_ids[0]):], skip_special_tokens=False))
# --> `Sure` 

# using our PairRM for best-of-n sampling
blender = llm_blender.Blender()
blender.loadranker("llm-blender/PairRM") # load ranker checkpoint
outputs = blender.best_of_n_generate(model, tokenizer, prompts, n=10)

print("### Prompt:")
print(prompts[0])
print("### best-of-n generations:")
print(outputs[0])
# --> 
""" 
Sure, here's a joke about OpenAI:

Why did OpenAI decide to hire a mime as their new AI researcher?

Because they wanted someone who could communicate complex ideas without making a sound!

(Note: This is a joke, not a reflection of OpenAI's actual hiring practices.)
"""

import os
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
from llm_blender.pair_ranker.pairrm import DebertaV2PairRM # or copy the DebertaV2PairRM definition here, https://github.com/yuchenlin/LLM-Blender/blob/main/llm_blender/pair_ranker/pairrm.py
from transformers import AutoTokenizer
from typing import List
pairrm = DebertaV2PairRM.from_pretrained("llm-blender/PairRM-hf", device_map="cuda:0").eval()
tokenizer = AutoTokenizer.from_pretrained('llm-blender/PairRM-hf')
source_prefix = "<|source|>"
cand1_prefix = "<|candidate1|>"
cand2_prefix = "<|candidate2|>"
inputs = ["hello!", "I love you!"]
candidates_A = ["hi!", "I hate you!"]
candidates_B = ["f**k off!", "I love you, too!"]
def tokenize_pair(sources:List[str], candidate1s:List[str], candidate2s:List[str], source_max_length=1224, candidate_max_length=412):
    ids = []
    assert len(sources) == len(candidate1s) == len(candidate2s)
    max_length = source_max_length + 2 * candidate_max_length
    for i in range(len(sources)):
        source_ids = tokenizer.encode(source_prefix + sources[i], max_length=source_max_length, truncation=True)
        candidate_max_length = (max_length - len(source_ids)) // 2
        candidate1_ids = tokenizer.encode(cand1_prefix + candidate1s[i], max_length=candidate_max_length, truncation=True)
        candidate2_ids = tokenizer.encode(cand2_prefix + candidate2s[i], max_length=candidate_max_length, truncation=True)
        ids.append(source_ids + candidate1_ids + candidate2_ids)
    encodings = tokenizer.pad({"input_ids": ids}, return_tensors="pt", padding="max_length", max_length=max_length)
    return encodings

encodings = tokenize_pair(inputs, candidates_A, candidates_B)
encodings = {k:v.to(pairrm.device) for k,v in encodings.items()}
outputs = pairrm(**encodings)
logits = outputs.logits.tolist()
comparison_results = outputs.logits > 0
print(logits)
# [1.9003021717071533, -1.2547134160995483]
print(comparison_results)
# tensor([ True, False], device='cuda:0'), which means whether candidate A is better than candidate B for each input