Quantization made by Richard Erkhov.

[Github](https://github.com/RichardErkhov)

[Discord](https://discord.gg/pvy7H8DZMG)

[Request more models](https://github.com/RichardErkhov/quant_request)


NeuralSynthesis-7B-v0.2 - bnb 4bits
- Model creator: https://huggingface.co/Kukedlc/
- Original model: https://huggingface.co/Kukedlc/NeuralSynthesis-7B-v0.2/




Original model description:
---
tags:
- merge
- mergekit
- lazymergekit
license: apache-2.0
---

# NeuralSynthesis-7B-v0.2

![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d71ab4089bc502ceb44d29/ID4yrGgmKZzqctPPkT4Dp.png)

NeuralSynthesis-7B-v0.2 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):

## 🧩 Configuration

```yaml
models:
  - model: Kukedlc/Fasciculus-Arcuatus-7B-slerp
  - model: Gille/StrangeMerges_30-7B-slerp
  - model: automerger/OgnoExperiment27-7B
  - model: Kukedlc/Jupiter-k-7B-slerp
  - model: Kukedlc/Neural-4-QA-7b
  - model: Kukedlc/NeuralSynthesis-7B-v0.1
merge_method: model_stock
base_model: Kukedlc/NeuralSynthesis-7B-v0.1
dtype: bfloat16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Kukedlc/NeuralSynthesis-7B-v0.2"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```