|
|
--- |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- moe |
|
|
- frankenmoe |
|
|
- merge |
|
|
- mergekit |
|
|
- lazymergekit |
|
|
- mlabonne/AlphaMonarch-7B |
|
|
- FPHam/Karen_TheEditor_V2_STRICT_Mistral_7B |
|
|
- SanjiWatsuki/Kunoichi-DPO-v2-7B |
|
|
- OmnicromsBrain/NeuralStar-7b-Lazy |
|
|
base_model: |
|
|
- mlabonne/AlphaMonarch-7B |
|
|
- FPHam/Karen_TheEditor_V2_STRICT_Mistral_7B |
|
|
- SanjiWatsuki/Kunoichi-DPO-v2-7B |
|
|
- OmnicromsBrain/NeuralStar-7b-Lazy |
|
|
--- |
|
|
|
|
|
%3C!-- HTML_TAG_END --> |
|
|
|
|
|
# NeuralStar_AlphaWriter_4x7b |
|
|
|
|
|
I was blown away by the writing results I was getting from mlabonne/Beyonder-4x7B-v3 while writing in [NovelCrafter](https://www.novelcrafter.com). |
|
|
|
|
|
Inspired by his [LLM Course](https://github.com/mlabonne/llm-course) and fueled by his [LazyMergeKit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb). |
|
|
I couldnt help but wonder what a writing model would be like if all 4 “experts” excelled in creative writing. |
|
|
|
|
|
I present NeuralStar-AlphaWriter-4x7b: |
|
|
|
|
|
|
|
|
NeuralStar_AlphaWriter_4x7b is a Mixture of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing): |
|
|
* [mlabonne/AlphaMonarch-7B](https://huggingface.co/mlabonne/AlphaMonarch-7B) |
|
|
* [FPHam/Karen_TheEditor_V2_STRICT_Mistral_7B](https://huggingface.co/FPHam/Karen_TheEditor_V2_STRICT_Mistral_7B) |
|
|
* [SanjiWatsuki/Kunoichi-DPO-v2-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-DPO-v2-7B) |
|
|
* [OmnicromsBrain/NeuralStar-7b-Lazy](https://huggingface.co/OmnicromsBrain/NeuralStar-7b-Lazy) |
|
|
|
|
|
## ⚡ Quantized Models |
|
|
|
|
|
Thanks to MRadermacher for the quantized models |
|
|
|
|
|
**.GGUF** https://huggingface.co/mradermacher/NeuralStar_AlphaWriter_4x7b-GGUF |
|
|
|
|
|
Q4_K_M and Q5_K_M .gguf [**Here**](https://huggingface.co/OmnicromsBrain/NeuralStar_AlphaWriter_4x7b-GGUF) created with [mlabonne/Autogguf](https://colab.research.google.com/drive/1P646NEg33BZy4BfLDNpTz0V0lwIU3CHu) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
## 🧩 Configuration |
|
|
|
|
|
```yaml |
|
|
base_model: mlabonne/AlphaMonarch-7B |
|
|
experts: |
|
|
- source_model: mlabonne/AlphaMonarch-7B |
|
|
positive_prompts: |
|
|
- "chat" |
|
|
- "assistant" |
|
|
- "tell me" |
|
|
- "explain" |
|
|
- "I want" |
|
|
- source_model: FPHam/Karen_TheEditor_V2_STRICT_Mistral_7B |
|
|
positive_prompts: |
|
|
- "edit" |
|
|
- "rewrite" |
|
|
- "evaluate" |
|
|
- "spelling" |
|
|
- "grammer" |
|
|
- source_model: SanjiWatsuki/Kunoichi-DPO-v2-7B |
|
|
positive_prompts: |
|
|
- "storywriting" |
|
|
- "write" |
|
|
- "scene" |
|
|
- "prose" |
|
|
- "character" |
|
|
- source_model: OmnicromsBrain/NeuralStar-7b-Lazy |
|
|
positive_prompts: |
|
|
- "codex" |
|
|
- "plot" |
|
|
- "outline" |
|
|
- "scenebeat" |
|
|
- "count" |
|
|
``` |
|
|
|
|
|
## 💻 Usage |
|
|
|
|
|
```python |
|
|
!pip install -qU transformers bitsandbytes accelerate |
|
|
|
|
|
from transformers import AutoTokenizer |
|
|
import transformers |
|
|
import torch |
|
|
|
|
|
model = "OmnicromsBrain/NeuralStar_AlphaWriter_4x7b" |
|
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model) |
|
|
pipeline = transformers.pipeline( |
|
|
"text-generation", |
|
|
model=model, |
|
|
model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True}, |
|
|
) |
|
|
|
|
|
messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}] |
|
|
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) |
|
|
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"]) |
|
|
``` |
