80 lines
2.2 KiB
Markdown
80 lines
2.2 KiB
Markdown
---
|
|
tags:
|
|
- merge
|
|
- mergekit
|
|
- lazymergekit
|
|
base_model:
|
|
- mlabonne/AlphaMonarch-7B
|
|
- Nexusflow/Starling-LM-7B-beta
|
|
license: apache-2.0
|
|
language:
|
|
- en
|
|
---
|
|
|
|
# StarMonarch-7B
|
|
|
|
# Description
|
|
|
|
StarMonarch-7B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
|
* [mlabonne/AlphaMonarch-7B](https://huggingface.co/mlabonne/AlphaMonarch-7B)
|
|
* [Nexusflow/Starling-LM-7B-beta](https://huggingface.co/Nexusflow/Starling-LM-7B-beta)
|
|
|
|
This model uses a context window of 8k. Special thanks to mlabonne and Nexusflow for the models.
|
|
|
|
## 🏆 Open LLM Leaderboard Evaluation Results
|
|
|
|
| Metric |Value|
|
|
|---------------------------------|----:|
|
|
|Avg. |74.45|
|
|
|AI2 Reasoning Challenge (25-Shot)|71.25|
|
|
|HellaSwag (10-Shot) |87.00|
|
|
|MMLU (5-Shot) |65.48|
|
|
|TruthfulQA (0-shot) |67.20|
|
|
|Winogrande (5-shot) |82.16|
|
|
|GSM8k (5-shot) |73.62|
|
|
|
|
## 🧩 Configuration
|
|
|
|
```yaml
|
|
slices:
|
|
- sources:
|
|
- model: mlabonne/AlphaMonarch-7B
|
|
layer_range: [0, 32]
|
|
- model: Nexusflow/Starling-LM-7B-beta
|
|
layer_range: [0, 32]
|
|
merge_method: slerp
|
|
base_model: mlabonne/AlphaMonarch-7B
|
|
parameters:
|
|
t:
|
|
- filter: self_attn
|
|
value: [0, 0.5, 0.3, 0.7, 1]
|
|
- filter: mlp
|
|
value: [1, 0.5, 0.7, 0.3, 0]
|
|
- value: 0.5
|
|
dtype: bfloat16
|
|
```
|
|
|
|
## 💻 Usage
|
|
|
|
```python
|
|
!pip install -qU transformers accelerate
|
|
|
|
from transformers import AutoTokenizer
|
|
import transformers
|
|
import torch
|
|
|
|
model = "Ppoyaa/StarMonarch-7B"
|
|
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"])
|
|
``` |