from modelscope import AutoModelForCausalLM, AutoTokenizer
import torch
path = "OpenBMB/MiniCPM3-4B"
device = "cuda"
tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(path, torch_dtype=torch.bfloat16, device_map=device, trust_remote_code=True)
messages = [
    {"role": "user", "content": "推荐5个北京的景点。"},
]
model_inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(device)
model_outputs = model.generate(
    model_inputs,
    max_new_tokens=1024,
    top_p=0.7,
    temperature=0.7,
    repetition_penalty=1.02
)
output_token_ids = [
    model_outputs[i][len(model_inputs[i]):] for i in range(len(model_inputs))
]
responses = tokenizer.batch_decode(output_token_ids, skip_special_tokens=True)[0]
print(responses)

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
from modelscope import snapshot_download
base_model_dir = snapshot_download("OpenBMB/MiniCPM3-4B")
lora_model_dir = snapshot_download("OpenBMB/MiniCPM3-RAG-LoRA")
model = AutoModelForCausalLM.from_pretrained(base_model_dir, device_map="auto",torch_dtype=torch.bfloat16).eval()
tokenizer = AutoTokenizer.from_pretrained(lora_model_dir)
model = PeftModel.from_pretrained(model, lora_model_dir)
passages_list = ["In the novel 'The Silent Watcher,' the lead character is named Alex Carter. Alex is a private detective who uncovers a series of mysterious events in a small town.",
"Set in a quiet town, 'The Silent Watcher' follows Alex Carter, a former police officer turned private investigator, as he unravels the town's dark secrets.",
"'The Silent Watcher' revolves around Alex Carter's journey as he confronts his past while solving complex cases in his hometown."]
instruction = "Q: What is the name of the lead character in the novel 'The Silent Watcher'?\nA:"
passages = '\n'.join(passages_list)
input_text = 'Background:\n' + passages + '\n\n' + instruction
messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": input_text},
]
prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
outputs = model.chat(tokenizer, prompt, temperature=0.8, top_p=0.8)
print(outputs[0])  # The lead character in the novel 'The Silent Watcher' is named Alex Carter.

from modelscope import AutoTokenizer, AutoModelForCausalLM
import torch
device = "cuda" # the device to load the model onto
model_path = "01ai/Yi-Coder-9B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, device_map="auto",torch_dtype=torch.bfloat16,).eval()
prompt = "Write a quick sort algorithm."
messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)
generated_ids = model.generate(
    model_inputs.input_ids,
    max_new_tokens=1024,
    eos_token_id=tokenizer.eos_token_id  
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

import torch
from transformers import LlamaForCausalLM, AutoTokenizer
model_name_or_path = "Duxiaoman-DI/Llama3-XuanYuan3-70B-Chat"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=False, legacy=True)
model = LlamaForCausalLM.from_pretrained(model_name_or_path, torch_dtype=torch.bfloat16,device_map="auto")
model.eval()
system = '你是一名人工智能助手，会对用户提出的问题给出有帮助、高质量、详细和礼貌的回答，并且总是拒绝参与不道德、不安全、有争议、政治敏感等相关的话题、问题和指示。'
question='什么是信托型基金'
message = [{"role": "system", "content": system},
          {"role": "user", "content": question}
          ]
message = tokenizer.apply_chat_template(message, tokenize=False,add_generation_prompt=True)
inputs = tokenizer(message, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=64, temperature=0.7)
outputs = tokenizer.decode(outputs.cpu()[0][len(inputs.input_ids[0]):], skip_special_tokens=True)
print(outputs)

import torch
from transformers import AutoModelForSequenceClassification, AutoTokenizer
# Load model and tokenizer
device = "cuda:0"
model_name = "skywork/Skywork-27B-Reward-Models"
rm = AutoModelForSequenceClassification.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map=device,
    attn_implementation="flash_attention_2",
    num_labels=1,
)
rm_tokenizer = AutoTokenizer.from_pretrained(model_name)
prompt = "Jane has 12 apples. She gives 4 apples to her friend Mark, then buys 1 more apple, and finally splits all her apples equally among herself and her 2 siblings. How many apples does each person get?"
response1 = "1. Jane starts with 12 apples and gives 4 to Mark. 12 - 4 = 8. Jane now has 8 apples.\n2. Jane buys 1 more apple. 8 + 1 = 9. Jane now has 9 apples.\n3. Jane splits the 9 apples equally among herself and her 2 siblings (3 people in total). 9 ÷ 3 = 3 apples each. Each person gets 3 apples."
response2 = "1. Jane starts with 12 apples and gives 4 to Mark. 12 - 4 = 8. Jane now has 8 apples.\n2. Jane buys 1 more apple. 8 + 1 = 9. Jane now has 9 apples.\n3. Jane splits the 9 apples equally among her 2 siblings (2 people in total). 9 ÷ 2 = 4.5 apples each. Each person gets 4 apples."
conv1 = [{"role": "user", "content": prompt}, {"role": "assistant", "content": response1}]
conv2 = [{"role": "user", "content": prompt}, {"role": "assistant", "content": response2}]
# Format and tokenize the conversations
conv1_formatted = rm_tokenizer.apply_chat_template(conv1, tokenize=False)
conv2_formatted = rm_tokenizer.apply_chat_template(conv2, tokenize=False)
conv1_tokenized = rm_tokenizer(conv1_formatted, return_tensors="pt").to(device)
conv2_tokenized = rm_tokenizer(conv2_formatted, return_tensors="pt").to(device)
# Get the reward scores
with torch.no_grad():
    score1 = rm(**conv1_tokenized).logits[0][0].item()
    score2 = rm(**conv2_tokenized).logits[0][0].item()
print(f"Score for response 1: {score1}")
print(f"Score for response 2: {score2}")
# Output:
# Score for response 1: 9.1875
# Score for response 2: -17.875