Text Generation
PEFT
Safetensors
llama-2
Eval Results
Edit model card

Llama-2-70B-Instruct-v0.1

This instruction model was built via parameter-efficient QLoRA finetuning of llama-2-70b on the first 25k rows of ehartford/dolphin (an open-source implementation of Microsoft's Orca). Finetuning was executed on a single H100 (80 GB PCIe) for roughly 17 hours on the Lambda Labs platform.

Note: This model was ranked 6th on πŸ€—'s Open LLM Leaderboard in Aug 2023

Helpful links

  • Model license: Llama 2 Community License Agreement
  • Basic usage: notebook

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 65.72
AI2 Reasoning Challenge (25-Shot) 69.62
HellaSwag (10-Shot) 86.82
MMLU (5-Shot) 69.18
TruthfulQA (0-shot) 57.43
Winogrande (5-shot) 83.90
GSM8k (5-shot) 27.37

Example prompts and responses

Example 1:

User:

You are a helpful assistant. Write me a numbered list of things to do in New York City.\n

Llama-2-70B-Instruct-v0.1-peft:

  1. Visit the Statue of Liberty: Take a ferry to Liberty Island and see the iconic symbol of freedom and democracy.
  2. Explore Central Park: Enjoy the lush greenery, take a stroll, or rent a bike to explore the park's many attractions, such as the Central Park Zoo and Strawberry Fields.
  3. Visit the Empire State Building: Take an elevator to the observation deck for breathtaking views of the city.
  4. Walk the Brooklyn Bridge: Cross the historic bridge and enjoy the stunning views of the Manhattan skyline.
  5. Experience Times Square: Take in the bright lights, billboards, and bustling energy of this iconic intersection.
  6. Visit the Metropolitan Museum of Art: Explore the vast collection of art and artifacts from around the world.
  7. Take a food tour: Sample the diverse cuisine of New York City, from pizza to bagels to ethnic specialties.
  8. Attend a Broadway show: Enjoy a world-class performance in the heart of the Theater District.

Example 2:

User:

You are a helpful assistant. Write a short email inviting my friends to a dinner party on Friday. Respond succinctly.\n

Llama-2-70B-Instruct-v0.1-peft:

Subject: Dinner Party Invitation - Friday, 7 PM

Dear Friends,

I hope this email finds you well! I'm excited to invite you to a dinner party at my place this Friday, at 7 PM. We'll have a delicious meal, great company, and lots of fun. Please let me know if you can make it, so I can plan accordingly.

Looking forward to seeing you all!

Kind regards, Your Name

P.S. Please let me know if you have any dietary restrictions or allergies.


Example 3:

User:

You are a helpful assistant. Tell me a recipe for vegan banana bread.\n

Llama-2-70B-Instruct-v0.1-peft:

Sure! Here's a delicious and easy vegan banana bread recipe:

Ingredients:

  • 2 cups all-purpose flour
  • 1/2 cup sugar
  • 1/2 cup vegan butter (such as Earth Balance)
  • 1/2 cup vegan milk (such as almond milk)
  • 1/2 cup unsweetened applesauce
  • 1/2 cup mashed ripe bananas (about 2 medium bananas)
  • 1 teaspoon baking soda
  • 1/2 teaspoon salt
  • 1/2 teaspoon ground cinnamon
  • 1/2 teaspoon ground nutmeg
  • 1/2 teaspoon ground cloves
  • 1/2 cup chopped walnuts (optional)

Instructions:

  1. Preheat the oven to 350Β°F (175Β°C). Grease a 9x5-inch loaf pan with vegan butter or cooking spray.
  2. In a large bowl, mix together the flour, sugar, vegan butter, vegan milk, applesauce, bananas, baking soda, salt, cinnamon, nutmeg, and cloves. Stir until well combined.
  3. Fold in the chopped walnuts, if using.
  4. Pour the batter into the prepared loaf pan.
  5. Bake for 50-60 minutes, or until a toothpick inserted into the center of the bread comes out clean.
  6. Let the bread cool in the pan for 10 minutes before transferring it to a wire rack to cool completely.
  7. Slice and enjoy!

Note: You can also add chocolate chips, dried fruit, or other mix-ins to the batter for extra flavor and texture. Enjoy your vegan banana bread!


Model description

The architecture is a modification of a standard decoder-only transformer and was trained as a causal language model (clm).

The llama-2-70b models have been modified from a standard transformer in the following ways:

Hyperparameter Value
n_parameters 70B
tokens 2.0T
vocab size 32000
sequence length 4096
grouped-query attention βœ”οΈ

Pre-training data

For more details on the pretraining process, see Llama-2-70b-hf.

The data was tokenized using the Llama-2-70b-hf tokenizer.

Limitations and biases

The following language is modified from EleutherAI's GPT-NeoX-20B

This model can produce factually incorrect output, and should not be relied on to produce factually accurate information. This model was trained on various public datasets. While great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs.

Basic usage

!pip install -q -U huggingface_hub peft transformers torch accelerate
from huggingface_hub import notebook_login
import torch
from peft import PeftModel, PeftConfig
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
    BitsAndBytesConfig,
    pipeline,
)

notebook_login()
peft_model_id = "dfurman/llama-2-13b-dolphin-peft"
config = PeftConfig.from_pretrained(peft_model_id)

bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.bfloat16,
)

model = AutoModelForCausalLM.from_pretrained(
    config.base_model_name_or_path,
    quantization_config=bnb_config,
    use_auth_token=True,
    device_map="auto",
)

tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path, use_fast=True)
tokenizer.pad_token = tokenizer.eos_token

model = PeftModel.from_pretrained(model, peft_model_id)

format_template = "You are a helpful assistant. {query}\n"
# First, format the prompt
query = "Tell me a recipe for vegan banana bread."
prompt = format_template.format(query=query)

# Inference can be done using model.generate
print("\n\n*** Generate:")

input_ids = tokenizer(prompt, return_tensors="pt").input_ids.cuda()
with torch.autocast("cuda", dtype=torch.bfloat16):
    output = model.generate(
        input_ids=input_ids,
        max_new_tokens=512,
        do_sample=True,
        temperature=0.7,
        return_dict_in_generate=True,
        eos_token_id=tokenizer.eos_token_id,
        pad_token_id=tokenizer.pad_token_id,
        repetition_penalty=1.2,
    )

print(tokenizer.decode(output["sequences"][0], skip_special_tokens=True))

Runtime tests

runtime / 50 tokens (sec) GPU attn torch dtype VRAM (GB)
4.50 1x H100 (80 GB PCIe) torch nf4 39

The above runtime stats were generated from this notebook.

Acknowledgements

This model was finetuned by Daniel Furman on July 23, 2023 and is intended primarily for research purposes.

Disclaimer

The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please cosult an attorney before using this model for commercial purposes.

Meta citation for llama-2 blog

@online{Meta2023Introducing,
    author    = {Meta AI},
    title     = {Meta and Microsoft Introduce the Next Generation of Llama},
    year      = {2023},
    url       = {https://about.fb.com/news/2023/07/llama-2/},
    note      = {Accessed: 2023-07-24},
    urldate   = {2023-07-24}
}

Framework versions

  • PEFT 0.5.0.dev0
Downloads last month
102
Inference Examples
Inference API (serverless) has been turned off for this model.

Model tree for dfurman/Llama-2-70B-Instruct-v0.1

Adapter
(21)
this model

Dataset used to train dfurman/Llama-2-70B-Instruct-v0.1

Spaces using dfurman/Llama-2-70B-Instruct-v0.1 21

Collection including dfurman/Llama-2-70B-Instruct-v0.1

Evaluation results