Edit model card

Nous-Hermes-2-Yi-34B-pruned2.4

This repo contains model files for Nous Hermes 2 - Yi-34B optimized for NM-vLLM, a high-throughput serving engine for compressed LLMs.

This model was pruned with SparseGPT, using SparseML.

Inference

Install NM-vLLM for fast inference and low memory-usage:

pip install nm-vllm[sparse]

Run in a Python pipeline for local inference:

from vllm import LLM, SamplingParams

model = LLM("nm-testing/Nous-Hermes-2-Yi-34B-pruned2.4", sparsity="semi_structured_sparse_w16a16")
prompt = "How to make banana bread?"
formatted_prompt =  f"<|im_start|>User:{prompt}\n<|im_start|>assistant:\n"

sampling_params = SamplingParams(max_tokens=100, temperature=0)
outputs = model.generate(formatted_prompt, sampling_params=sampling_params)
print(outputs[0].outputs[0].text)
"""
To make banana bread, follow these steps:
1. Gather the ingredients:
- 2 ripe bananas
- 2 cups of flour
- 1 teaspoon of baking powder
- 1 teaspoon of salt
- 1 teaspoon of sugar
- 1 teaspoon of vanilla extract
2. Preheat the oven to 350°F.
3. In a mixing bowl, combine the flour, baking powder, salt, sugar, and vanilla extract.
4.
"""

Prompt template

<|im_start|>User:{prompt}\n<|im_start|>assistant:\n

Sparsification

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

Install SparseML:

git clone https://github.com/neuralmagic/sparseml
pip install -e "sparseml[transformers]"

Replace the recipe as you like and run this one-shot compression script to apply SparseGPT:

import sparseml.transformers

original_model_name = "NousResearch/Nous-Hermes-2-Yi-34B"
calibration_dataset = "open_platypus"
output_directory = "output/"

recipe = """
test_stage:
  obcq_modifiers:
    SparseGPTModifier:
      sparsity: 0.5
      sequential_update: true
      mask_structure: '2:4'
      targets: ['re:model.layers.\d*$']
"""

# Apply SparseGPT to the model
sparseml.transformers.oneshot(
    model=original_model_name,
    dataset=calibration_dataset,
    recipe=recipe,
    output_dir=output_directory,
)

Slack

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

Downloads last month
2
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for neuralmagic/Nous-Hermes-2-Yi-34B-pruned2.4

Base model

01-ai/Yi-34B
Finetuned
(3)
this model