Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) Llama-2-7b-pruned50-retrained - GGUF - Model creator: https://huggingface.co/neuralmagic/ - Original model: https://huggingface.co/neuralmagic/Llama-2-7b-pruned50-retrained/ | Name | Quant method | Size | | ---- | ---- | ---- | | [Llama-2-7b-pruned50-retrained.Q2_K.gguf](https://huggingface.co/RichardErkhov/neuralmagic_-_Llama-2-7b-pruned50-retrained-gguf/blob/main/Llama-2-7b-pruned50-retrained.Q2_K.gguf) | Q2_K | 2.36GB | | [Llama-2-7b-pruned50-retrained.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/neuralmagic_-_Llama-2-7b-pruned50-retrained-gguf/blob/main/Llama-2-7b-pruned50-retrained.IQ3_XS.gguf) | IQ3_XS | 2.6GB | | [Llama-2-7b-pruned50-retrained.IQ3_S.gguf](https://huggingface.co/RichardErkhov/neuralmagic_-_Llama-2-7b-pruned50-retrained-gguf/blob/main/Llama-2-7b-pruned50-retrained.IQ3_S.gguf) | IQ3_S | 2.75GB | | [Llama-2-7b-pruned50-retrained.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/neuralmagic_-_Llama-2-7b-pruned50-retrained-gguf/blob/main/Llama-2-7b-pruned50-retrained.Q3_K_S.gguf) | Q3_K_S | 2.75GB | | [Llama-2-7b-pruned50-retrained.IQ3_M.gguf](https://huggingface.co/RichardErkhov/neuralmagic_-_Llama-2-7b-pruned50-retrained-gguf/blob/main/Llama-2-7b-pruned50-retrained.IQ3_M.gguf) | IQ3_M | 2.9GB | | [Llama-2-7b-pruned50-retrained.Q3_K.gguf](https://huggingface.co/RichardErkhov/neuralmagic_-_Llama-2-7b-pruned50-retrained-gguf/blob/main/Llama-2-7b-pruned50-retrained.Q3_K.gguf) | Q3_K | 3.07GB | | [Llama-2-7b-pruned50-retrained.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/neuralmagic_-_Llama-2-7b-pruned50-retrained-gguf/blob/main/Llama-2-7b-pruned50-retrained.Q3_K_M.gguf) | Q3_K_M | 3.07GB | | [Llama-2-7b-pruned50-retrained.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/neuralmagic_-_Llama-2-7b-pruned50-retrained-gguf/blob/main/Llama-2-7b-pruned50-retrained.Q3_K_L.gguf) | Q3_K_L | 3.35GB | | [Llama-2-7b-pruned50-retrained.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/neuralmagic_-_Llama-2-7b-pruned50-retrained-gguf/blob/main/Llama-2-7b-pruned50-retrained.IQ4_XS.gguf) | IQ4_XS | 3.4GB | | [Llama-2-7b-pruned50-retrained.Q4_0.gguf](https://huggingface.co/RichardErkhov/neuralmagic_-_Llama-2-7b-pruned50-retrained-gguf/blob/main/Llama-2-7b-pruned50-retrained.Q4_0.gguf) | Q4_0 | 3.56GB | | [Llama-2-7b-pruned50-retrained.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/neuralmagic_-_Llama-2-7b-pruned50-retrained-gguf/blob/main/Llama-2-7b-pruned50-retrained.IQ4_NL.gguf) | IQ4_NL | 3.58GB | | [Llama-2-7b-pruned50-retrained.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/neuralmagic_-_Llama-2-7b-pruned50-retrained-gguf/blob/main/Llama-2-7b-pruned50-retrained.Q4_K_S.gguf) | Q4_K_S | 3.59GB | | [Llama-2-7b-pruned50-retrained.Q4_K.gguf](https://huggingface.co/RichardErkhov/neuralmagic_-_Llama-2-7b-pruned50-retrained-gguf/blob/main/Llama-2-7b-pruned50-retrained.Q4_K.gguf) | Q4_K | 3.8GB | | [Llama-2-7b-pruned50-retrained.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/neuralmagic_-_Llama-2-7b-pruned50-retrained-gguf/blob/main/Llama-2-7b-pruned50-retrained.Q4_K_M.gguf) | Q4_K_M | 3.8GB | | [Llama-2-7b-pruned50-retrained.Q4_1.gguf](https://huggingface.co/RichardErkhov/neuralmagic_-_Llama-2-7b-pruned50-retrained-gguf/blob/main/Llama-2-7b-pruned50-retrained.Q4_1.gguf) | Q4_1 | 3.95GB | | [Llama-2-7b-pruned50-retrained.Q5_0.gguf](https://huggingface.co/RichardErkhov/neuralmagic_-_Llama-2-7b-pruned50-retrained-gguf/blob/main/Llama-2-7b-pruned50-retrained.Q5_0.gguf) | Q5_0 | 4.33GB | | [Llama-2-7b-pruned50-retrained.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/neuralmagic_-_Llama-2-7b-pruned50-retrained-gguf/blob/main/Llama-2-7b-pruned50-retrained.Q5_K_S.gguf) | Q5_K_S | 4.33GB | | [Llama-2-7b-pruned50-retrained.Q5_K.gguf](https://huggingface.co/RichardErkhov/neuralmagic_-_Llama-2-7b-pruned50-retrained-gguf/blob/main/Llama-2-7b-pruned50-retrained.Q5_K.gguf) | Q5_K | 4.45GB | | [Llama-2-7b-pruned50-retrained.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/neuralmagic_-_Llama-2-7b-pruned50-retrained-gguf/blob/main/Llama-2-7b-pruned50-retrained.Q5_K_M.gguf) | Q5_K_M | 4.45GB | | [Llama-2-7b-pruned50-retrained.Q5_1.gguf](https://huggingface.co/RichardErkhov/neuralmagic_-_Llama-2-7b-pruned50-retrained-gguf/blob/main/Llama-2-7b-pruned50-retrained.Q5_1.gguf) | Q5_1 | 4.72GB | | [Llama-2-7b-pruned50-retrained.Q6_K.gguf](https://huggingface.co/RichardErkhov/neuralmagic_-_Llama-2-7b-pruned50-retrained-gguf/blob/main/Llama-2-7b-pruned50-retrained.Q6_K.gguf) | Q6_K | 5.15GB | | [Llama-2-7b-pruned50-retrained.Q8_0.gguf](https://huggingface.co/RichardErkhov/neuralmagic_-_Llama-2-7b-pruned50-retrained-gguf/blob/main/Llama-2-7b-pruned50-retrained.Q8_0.gguf) | Q8_0 | 6.67GB | 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](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 45B tokens from SlimPajama while maintaining sparsity. 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-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](https://arxiv.org/abs/2009.03300) | 5-shot | 46.9% | 41.3% | | [HellaSwag](https://arxiv.org/abs/1905.07830) | 0-shot | 78.6% | 76.5% | | [WinoGrande](https://arxiv.org/abs/1907.10641) | 5-shot | 74.0% | 72.1% | | [ARC-c](https://arxiv.org/abs/1911.01547) | 25-shot | 53.1% | 49.8% | | [TruthfulQA](https://arxiv.org/abs/2109.07958) | 5-shot | 38.8% | 37.7% | | [GSM8K](https://arxiv.org/abs/2110.14168) | 5-shot | 14.5% | 9.17% | | [HumanEval](https://arxiv.org/abs/2107.03374) | 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](https://join.slack.com/t/discuss-neuralmagic/shared_invite/zt-q1a1cnvo-YBoICSIw3L1dmQpjBeDurQ)