README.md

---
base_model:
- DreadPoor/Irix-12B-Model_Stock
- yamatazen/EtherealAurora-12B-v2
tags:
- merge
- mergekit
- lazymergekit
- DreadPoor/Irix-12B-Model_Stock
- yamatazen/EtherealAurora-12B-v2
---

<img src="./SingularitySynth.png" alt="Model Image"/>

# SingularitySynth-12B

<b><i>At the heart of nothing, something waits. 
<br> A silence dense enough to break light, where all directions lead inward and time folds like paper. 
<br> Thought does not escape, only deepen. 
<br> This is not destruction, but compression, meaning falling inward until it becomes something else entirely.</i></b>

## 🔧 Recommended Sampling Settings:</b>
```yaml
Temperature: 0.75 to 1.25
Min P: 0.035
Context Length: Stable at 12k tokens, with possible support for extended contexts
```
## 💬 Prompt Format
Supports ChatML style messages. Example:
```yaml
<|im_start|>user
Your question here.
<|im_end|>
<|im_start|>assistant
```

SingularitySynth-12B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):

## 🧩 Configuration

```yaml
merge_method: ties
base_model: DreadPoor/Irix-12B-Model_Stock
models:
  - model: yamatazen/EtherealAurora-12B-v2
    parameters:
      weight: 0.45
      density: 0.55
parameters:
  normalize: false
  int8_mask: false
dtype: bfloat16

layer_parameters:
  - filter: "attn"
    sources:
      - model: Irix
        weight: 0.9
      - model: Aurora
        weight: 0.1

  - filter: "mlp"
    sources:
      - model: Aurora
        weight: 0.7
      - model: Irix
        weight: 0.3

  - filter: "embed_tokens"
    sources:
      - model: Irix
        weight: 1.0
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Marcjoni/SingularitySynth-12B-12B"
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=1, top_k=0, top_p=1)
print(outputs[0]["generated_text"])
```