Views
No views yet
microsoft/orca-math-word-problems-200k: A large-scale dataset of mathematical word problems aimed at enhancing the model's numerical reasoning and problem-solving capabilities.ise-uiuc/Magicoder-Evol-Instruct-110K: A dataset designed to improve code generation and understanding, contributing to the model's programming language proficiency.sahil2801/CodeAlpaca-20k: A dataset focused on programming challenges to further refine the model's coding and logical reasoning skills.1!pip install -qU transformers accelerate
2
3from transformers import AutoTokenizer
4import transformers
5import torch
6
7model = "Kukedlc/NeuralExperiment-7b-MagicCoder-v7"
8messages = [{"role": "user", "content": "What is a large language model?"}]
9
10tokenizer = AutoTokenizer.from_pretrained(model)
11prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
12pipeline = transformers.pipeline(
13 "text-generation",
14 model=model,
15 torch_dtype=torch.float16,
16 device_map="auto",
17)
18
19outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
20print(outputs[0]["generated_text"])