87 lines
2.8 KiB
Markdown
87 lines
2.8 KiB
Markdown
---
|
|
base_model: teknium/OpenHermes-2.5-Mistral-7B
|
|
inference: true
|
|
model_type: mistral
|
|
quantized_by: mgoin
|
|
tags:
|
|
- nm-vllm
|
|
- sparse
|
|
---
|
|
|
|
## OpenHermes-2.5-Mistral-7B-pruned50
|
|
This repo contains model files for [OpenHermes-2.5-Mistral-7B](https://huggingface.co/NousResearch/Nous-Hermes-2-Yi-34B) optimized for [NM-vLLM](https://github.com/neuralmagic/nm-vllm), a high-throughput serving engine for compressed LLMs.
|
|
|
|
This model was pruned with [SparseGPT](https://arxiv.org/abs/2301.00774), using [SparseML](https://github.com/neuralmagic/sparseml).
|
|
|
|
## Inference
|
|
Install [NM-vLLM](https://github.com/neuralmagic/nm-vllm) for fast inference and low memory-usage:
|
|
```bash
|
|
pip install nm-vllm[sparse]
|
|
```
|
|
Run in a Python pipeline for local inference:
|
|
```python
|
|
from vllm import LLM, SamplingParams
|
|
|
|
model = LLM("nm-testing/OpenHermes-2.5-Mistral-7B-pruned2.4", sparsity="semi_structured_sparse_w16a16")
|
|
prompt = "How to make banana bread?"
|
|
formatted_prompt = f"<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"
|
|
|
|
sampling_params = SamplingParams(max_tokens=100)
|
|
outputs = model.generate(formatted_prompt, sampling_params=sampling_params)
|
|
print(outputs[0].outputs[0].text)
|
|
"""
|
|
In order to make banana bread, you will need to follow these steps:
|
|
|
|
1. Prepare the ingredients: You will need flour, sugar, eggs, and bananas.
|
|
2. Prepare your ingredients: Prepare your bananas, flour, sugar, and eggs by preparing them in their respective bowls, ready to prepare the banana bread.
|
|
3. Make the batter: You will prepare batter by combining the flour, sugar, eggs and bananas. This
|
|
"""
|
|
```
|
|
|
|
## Prompt template
|
|
|
|
```
|
|
<|im_start|>user
|
|
{prompt}<|im_end|>
|
|
<|im_start|>assistant
|
|
```
|
|
|
|
## Sparsification
|
|
For details on how this model was sparsified, see the `recipe.yaml` in this repo and follow the instructions below.
|
|
|
|
Install [SparseML](https://github.com/neuralmagic/sparseml):
|
|
```bash
|
|
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:
|
|
```python
|
|
import sparseml.transformers
|
|
|
|
original_model_name = "teknium/OpenHermes-2.5-Mistral-7B"
|
|
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](https://join.slack.com/t/discuss-neuralmagic/shared_invite/zt-q1a1cnvo-YBoICSIw3L1dmQpjBeDurQ) |