|
--- |
|
base_model: neuralmagic/Llama-2-7b-pruned50-retrained |
|
inference: true |
|
model_type: llama |
|
pipeline_tag: text-generation |
|
datasets: |
|
- cerebras/SlimPajama-627B |
|
tags: |
|
- sparse |
|
--- |
|
|
|
# Llama-2-7b-pruned70-retrained |
|
|
|
This repo contains model files for a [Llama 2 7B](https://huggingface.co/meta-llama/Llama-2-7b-hf) model that has had 50% of the parameters pruned in one-shot with [SparseGPT](https://arxiv.org/abs/2301.00774), then retrained by [Cerebras](https://huggingface.co/cerebras) with 50B tokens from SlimPajama while maintaining sparsity. It was then one-shot pruned to 70% sparsity and trained for another 100B tokens. |
|
|
|
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 has not been fine-tuned for instruction-following but 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("neuralmagic/Llama-2-7b-pruned70-retrained") |
|
model = AutoModelForCausalLM.from_pretrained("neuralmagic/Llama-2-7b-pruned70-retrained", device_map="auto") |
|
|
|
input_text = "Write me a poem about Machine Learning." |
|
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. [UPDATE] |
|
|
|
| Benchmark | Metric | Llama-2-7b | Llama-2-7b-pruned70-retrained | |
|
|------------------------------------------------|---------------|-------------|-------------------------------| |
|
| [MMLU](https://arxiv.org/abs/2009.03300) | 5-shot | 46.9% | 36.5% | |
|
| [HellaSwag](https://arxiv.org/abs/1905.07830) | 0-shot | 78.6% | 74.1% | |
|
| [WinoGrande](https://arxiv.org/abs/1907.10641) | 5-shot | 74.0% | 69.5% | |
|
| [ARC-c](https://arxiv.org/abs/1911.01547) | 25-shot | 53.1% | 45.4% | |
|
| [TruthfulQA](https://arxiv.org/abs/2109.07958) | 5-shot | 38.8% | 36.7% | |
|
| [GSM8K](https://arxiv.org/abs/2110.14168) | 5-shot | 14.5% | 8.0% | |
|
| [HumanEval](https://arxiv.org/abs/2107.03374) | pass@1 | 13.4% | 14.4% | |
|
|
|
## Model Training Details |
|
|
|
[UPDATE] |
|
|
|
## 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) |
