nm-testing/dopeyplats-1.1b-2T-v1-pruned50-quant-ds

DopeyPlats-1.1b V2- DeepSparse

This repo contains model files for DopeyPlats-1.1b V2 optimized for DeepSparse, a CPU inference runtime for sparse models.

This model was quantized and pruned with SparseGPT, using SparseML.

Inference

Install DeepSparse LLM for fast inference on CPUs:

pip install deepsparse-nightly[llm]

Run in a Python pipeline:

from deepsparse import TextGeneration

prompt = "How to make banana bread?"
formatted_prompt =  f"<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n"

model = TextGeneration(model_path="hf:neuralmagic/TinyLlama-1.1B-Chat-v0.4-pruned50-quant-ds")
print(model(formatted_prompt, max_new_tokens=200).generations[0].text)

"""
1. In a bowl, add 2 cups of flour, 1 cup of sugar, 1 cup of salt, and 1 cup of butter.
2. Mix the ingredients together.
3. Divide into equal parts.
4. Incorporate the banana into the mixture.
5. Prepare the mixture into a loaf.
6. Bake the loaf.
7. Remove the loaf from the oven.
8. Cut the loaf into pieces.
9. Store the pieces in a container.
10. Enjoy the banana bread!
"""

Prompt template

### Instruction:\n
{prompt}
### Response:\n

Sparsification

For details on how this model was sparsified, see the recipe.yaml in this repo and follow the instructions below.

git clone https://github.com/neuralmagic/sparseml
pip install -e "sparseml[transformers]"
wget https://huggingface.co/neuralmagic/TinyLlama-1.1B-Chat-v0.4-pruned50-quant/raw/main/recipe.yaml # download recipe
python sparseml/src/sparseml/transformers/sparsification/obcq/obcq.py vihangd/dopeyplats-1.1b-2T-v open_platypus --recipe recipe.yaml --save True
python sparseml/src/sparseml/transformers/sparsification/obcq/export.py --task text-generation --model_path obcq_deployment 
cp deployment/model.onnx deployment/model-orig.onnx

Run this kv-cache injection to speed up the model at inference by caching the Key and Value states:

import os
import onnx
from sparseml.exporters.kv_cache_injector import KeyValueCacheInjector
input_file = "deployment/model-orig.onnx"
output_file = "deployment/model.onnx"
model = onnx.load(input_file, load_external_data=False)
model = KeyValueCacheInjector(model_path=os.path.dirname(input_file)).apply(model)
onnx.save(model, output_file)
print(f"Modified model saved to: {output_file}")

Follow the instructions on our One Shot With SparseML page for a step-by-step guide for performing one-shot quantization of large language models.

Slack

For further support, and discussions on these models and AI in general, join Neural Magic's Slack Community