Quantization made by Richard Erkhov.
Llama-2-7b-pruned50-retrained - GGUF
- Model creator: https://huggingface.co/neuralmagic/
- Original model: https://huggingface.co/neuralmagic/Llama-2-7b-pruned50-retrained/
Original model description:
base_model: meta-llama/Llama-2-7b-hf inference: true model_type: llama pipeline_tag: text-generation datasets: - cerebras/SlimPajama-627B tags: - sparse
Llama-2-7b-pruned50-retrained
This repo contains model files for a Llama 2 7B model that has had 50% of the parameters pruned in one-shot with SparseGPT, then retrained by Cerebras with 45B tokens from SlimPajama while maintaining sparsity.
Official model weights from Enabling High-Sparsity Foundational Llama Models with Efficient Pretraining and Deployment.
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.
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 or deepsparse.
# pip install transformers accelerate
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("neuralmagic/Llama-2-7b-pruned50-retrained")
model = AutoModelForCausalLM.from_pretrained("neuralmagic/Llama-2-7b-pruned50-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.
| Benchmark | Metric | Llama-2-7b | Llama-2-7b-pruned50-retrained |
|---|---|---|---|
| MMLU | 5-shot | 46.9% | 41.3% |
| HellaSwag | 0-shot | 78.6% | 76.5% |
| WinoGrande | 5-shot | 74.0% | 72.1% |
| ARC-c | 25-shot | 53.1% | 49.8% |
| TruthfulQA | 5-shot | 38.8% | 37.7% |
| GSM8K | 5-shot | 14.5% | 9.17% |
| HumanEval | pass@1 | 13.4% | 14.7% |
Model Training Details
Coming soon.
Help
For further support, and discussions on these models and AI in general, join Neural Magic's Slack Community
- Downloads last month
- 285