codellama

/

CodeLlama-7b-hf

like 331

Follow

Code Llama 519

I have this script, that prompts CodeLlama-7b-Instruct-hf:

from transformers import AutoTokenizer
import transformers
import torch

model = "meta-llama/CodeLlama-7b-Instruct-hf"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

sequences = pipeline(
    'Write a Python script using the model "'+model+'",  AutoTokenizer, transformer and torch.'
    + 'That Python script will start an HTTP server and take the prompt it receives from the body of a POST request.'
    + 'The result will be sent as response. Answer with the Python script',
    do_sample=True,
    top_k=10,
    temperature=0.1,
    top_p=0.95,
    num_return_sequences=1,
    eos_token_id=tokenizer.eos_token_id,
    max_length=512,
    truncation=True)
for seq in sequences:
    print(f"Result: {seq['generated_text']}")

The problem is I got this result:

Result: Write a Python script using the model "meta-llama/CodeLlama-7b-Instruct-hf",  AutoTokenizer, transformer and torch.That Python script will start an HTTP server and take the prompt it receives from the body of a POST request.The result will be sent as response. Answer with the Python script.

\begin{code}
import torch
from transformers import AutoTokenizer, AutoModelForSequenceClassification, TrainingArguments
from transformers import Trainer, TrainingArguments
from transformers import AutoModelForSequenceClassification, AutoTokenizer
import requests
import json
import numpy as np
import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
from torch.utils.data import Dataset, DataLoader
import pandas as pd
import numpy as np
import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
from torch.utils.data import Dataset, DataLoader
import pandas as pd
import numpy as np
import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
from torch.utils.data import Dataset, DataLoader
import pandas as pd
import numpy as np
import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
from torch.utils.data import Dataset, DataLoader
import pandas as pd
import numpy as np
import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
from torch.utils.data import Dataset, DataLoader
import pandas as pd
import numpy as np
import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
from torch.utils.data import Dataset, DataLoader
import pandas as pd
import numpy as np
import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
from torch

What did I miss?