LLaMa-2-70b-instruct-1024 model card
Model Details
- Developed by: Upstage
- Backbone Model: LLaMA-2
- Language(s): English
- Library: HuggingFace Transformers
- License: Fine-tuned checkpoints is licensed under the Non-Commercial Creative Commons license (CC BY-NC-4.0)
- Where to send comments: Instructions on how to provide feedback or comments on a model can be found by opening an issue in the Hugging Face community's model repository
- Contact: For questions and comments about the model, please email contact@upstage.ai
Dataset Details
Used Datasets
- Orca-style dataset
- No other data was used except for the dataset mentioned above
Prompt Template
### System:
{System}
### User:
{User}
### Assistant:
{Assistant}
Usage
- Tested on A100 80GB
- Our model can handle up to 10k+ input tokens, thanks to the
rope_scalingoption
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
tokenizer = AutoTokenizer.from_pretrained("upstage/Llama-2-70b-instruct")
model = AutoModelForCausalLM.from_pretrained(
"upstage/Llama-2-70b-instruct",
device_map="auto",
torch_dtype=torch.float16,
load_in_8bit=True,
rope_scaling={"type": "dynamic", "factor": 2} # allows handling of longer inputs
)
prompt = "### User:\nThomas is healthy, but he has to go to the hospital. What could be the reasons?\n\n### Assistant:\n"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
del inputs["token_type_ids"]
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
output = model.generate(**inputs, streamer=streamer, use_cache=True, max_new_tokens=float('inf'))
output_text = tokenizer.decode(output[0], skip_special_tokens=True)
Hardware and Software
- Hardware: We utilized an A100x8 * 4 for training our model
- Training Factors: We fine-tuned this model using a combination of the DeepSpeed library and the HuggingFace Trainer / HuggingFace Accelerate
Evaluation Results
Overview
- We conducted a performance evaluation based on the tasks being evaluated on the Open LLM Leaderboard.
We evaluated our model on four benchmark datasets, which include
ARC-Challenge,HellaSwag,MMLU, andTruthfulQAWe used the lm-evaluation-harness repository, specifically commit b281b0921b636bc36ad05c0b0b0763bd6dd43463 - We used MT-bench, a set of challenging multi-turn open-ended questions, to evaluate the models
Main Results
| Model | H4(Avg) | ARC | HellaSwag | MMLU | TruthfulQA | MT_Bench | |
|---|---|---|---|---|---|---|---|
| Llama-2-70b-instruct-v2(Ours, Open LLM Leaderboard) | 73 | 71.1 | 87.9 | 70.6 | 62.2 | 7.44063 | |
| Llama-2-70b-instruct (Ours, Open LLM Leaderboard) | 72.3 | 70.9 | 87.5 | 69.8 | 61 | 7.24375 | |
| llama-65b-instruct (Ours, Open LLM Leaderboard) | 69.4 | 67.6 | 86.5 | 64.9 | 58.8 | ||
| Llama-2-70b-hf | 67.3 | 67.3 | 87.3 | 69.8 | 44.9 | ||
| llama-30b-instruct-2048 (Ours, Open LLM Leaderboard) | 67.0 | 64.9 | 84.9 | 61.9 | 56.3 | ||
| llama-30b-instruct (Ours, Open LLM Leaderboard) | 65.2 | 62.5 | 86.2 | 59.4 | 52.8 | ||
| llama-65b | 64.2 | 63.5 | 86.1 | 63.9 | 43.4 | ||
| falcon-40b-instruct | 63.4 | 61.6 | 84.3 | 55.4 | 52.5 |
Scripts for H4 Score Reproduction
- Prepare evaluation environments:
# clone the repository
git clone https://github.com/EleutherAI/lm-evaluation-harness.git
# check out the specific commit
git checkout b281b0921b636bc36ad05c0b0b0763bd6dd43463
# change to the repository directory
cd lm-evaluation-harness
Ethical Issues
Ethical Considerations
- There were no ethical issues involved, as we did not include the benchmark test set or the training set in the model's training process
Contact Us
Why Upstage LLM?
- Upstage's LLM research has yielded remarkable results. As of August 1st, our 70B model has reached the top spot in openLLM rankings, marking itself as the current leading performer globally. Recognizing the immense potential in implementing private LLM to actual businesses, we invite you to easily apply private LLM and fine-tune it with your own data. For a seamless and tailored solution, please do not hesitate to reach out to us. ► click here to contact