|
--- |
|
base_model: neuralmagic/Llama-2-7b-pruned50-retrained |
|
inference: true |
|
model_type: llama |
|
pipeline_tag: text-generation |
|
datasets: |
|
- garage-bAInd/Open-Platypus |
|
- Open-Orca/OpenOrca |
|
- cognitivecomputations/dolphin |
|
tags: |
|
- sparse |
|
- instruct |
|
--- |
|
|
|
# Llama-2-7b-pruned50-retrained-instruct |
|
|
|
This repo contains a [50% sparse Llama 2 7B](https://huggingface.co/neuralmagic/Llama-2-7b-pruned50-retrained) finetuned for instruction-following tasks using a blend of the Platypus + Open Orca + Dolphin datasets. |
|
|
|
Official model weights from [Enabling High-Sparsity Foundational Llama Models with Efficient Pretraining and Deployment](https://arxiv.org/abs/2405.03594). |
|
|
|
**Authors**: Neural Magic, Cerebras |
|
|
|
## Usage |
|
|
|
Below we share some code snippets on how to get quickly started with running the model. |
|
|
|
### Sparse Transfer |
|
|
|
By leveraging a pre-sparsified model's structure, you can efficiently fine-tune on new data, leading to reduced hyperparameter tuning, training times, and computational costs. Learn about this process [here](https://neuralmagic.github.io/docs-v2/get-started/transfer). |
|
|
|
### Running the model |
|
|
|
This model may be run with the transformers library. For accelerated inference with sparsity, deploy with [nm-vllm](https://github.com/neuralmagic/nm-vllm) or [deepsparse](https://github.com/neuralmagic/deepsparse). |
|
|
|
```python |
|
# pip install transformers accelerate |
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
|
|
tokenizer = AutoTokenizer.from_pretrained("Llama-2-7b-pruned50-retrained-instruct") |
|
model = AutoModelForCausalLM.from_pretrained("Llama-2-7b-pruned50-retrained-instruct", device_map="auto") |
|
|
|
input_text = "Write a recipe for banana bread:\n" |
|
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda") |
|
|
|
outputs = model.generate(**input_ids) |
|
print(tokenizer.decode(outputs[0])) |
|
``` |
|
|
|
## Evaluation Benchmark Results |
|
|
|
Model evaluation metrics and results. |
|
|
|
| Benchmark | Metric | Llama-2-7b-instruct | Llama-2-7b-pruned50-retrained-instruct | |
|
|------------------------------------------------|---------------|-------------|-------------------------------| |
|
| [MMLU](https://arxiv.org/abs/2009.03300) | 5-shot | 48.60% | 45.10% | |
|
| [HellaSwag](https://arxiv.org/abs/1905.07830) | 10-shot | 79.45% | 78.86% | |
|
| [WinoGrande](https://arxiv.org/abs/1907.10641) | 5-shot | 75.69% | 72.61% | |
|
| [ARC-c](https://arxiv.org/abs/1911.01547) | 25-shot | 53.92% | 50.77% | |
|
| [TruthfulQA](https://arxiv.org/abs/2109.07958) | 0-shot | 43.63% | 44.40% | |
|
| [GSM8K](https://arxiv.org/abs/2110.14168) | 5-shot | 15.92% | 16.38% | |
|
|
|
## Model Training Details |
|
|
|
This model was obtained by sparse-tranfer of the sparse foundational model [Llama-2-7b-pruned50-retrained](https://huggingface.co/neuralmagic/Llama-2-7b-pruned70-retrained) on a blend of [Open Platypus](https://huggingface.co/datasets/garage-bAInd/Open-Platypus), 10% [Open Orca](https://huggingface.co/datasets/Open-Orca/OpenOrca) and 10% [Dolphin](https://huggingface.co/datasets/cognitivecomputations/dolphin) datasets. |
|
Training was perfomerd for 2 epochs. |
|
|
|
## Help |
|
|
|
For further support, and discussions on these models and AI in general, join [Neural Magic's Slack Community](https://join.slack.com/t/discuss-neuralmagic/shared_invite/zt-q1a1cnvo-YBoICSIw3L1dmQpjBeDurQ) |
