llama-2-7b-chat-finetuned

Model Card for Model ID

finetuned the LLAMA2-7b-chat model using LoRA.

This modelcard aims to be a base template for new models. It has been generated using this raw template.

Training Details

Training Data

Trained on this dataset

mlabonne/guanaco-llama2-1k

<!-- ## code --> <!-- !pip install transformers accelerate pip install transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "smd29/llama-2-7b-chat-finetuned" " prompt = "What is a large language model?" tokenizer = AutoTokenizer.from_pretrained(model) pipeline = transformers.pipeline( "text-generation", model=model, torch_dtype=torch.float16, device_map="auto", ) sequences = pipeline( f'<s>[INST] {prompt} [/INST]', do_sample=True, top_k=10, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id, max_length=200, ) for seq in sequences: print(f"Result: {seq['generated_text']}") prompt="explain me in a simple way,what the equation for finding the nth triangle number is and how it can be proved by using only high school level math. please give each step of a proof using LaTeX." sequences = pipeline( f'<s>[INST] {prompt} [/INST]', do_sample=True, top_k=10, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id, max_length=400, ) for seq in sequences: print(f"Result: {seq['generated_text']}")