|
--- |
|
tags: |
|
- merge |
|
- mergekit |
|
- lazymergekit |
|
- WizardLM/WizardMath-7B-V1.1 |
|
- mlabonne/NeuralDaredevil-7B |
|
- Kukedlc/Neural4gsm8k |
|
- Eric111/Mayo |
|
- Kukedlc/NeuralSirKrishna-7b |
|
base_model: |
|
- WizardLM/WizardMath-7B-V1.1 |
|
- mlabonne/NeuralDaredevil-7B |
|
- Kukedlc/Neural4gsm8k |
|
- Eric111/Mayo |
|
- Kukedlc/NeuralSirKrishna-7b |
|
license: apache-2.0 |
|
model-index: |
|
- name: NeuralSirKrishna-7b |
|
results: |
|
- task: |
|
type: text-generation |
|
name: Text Generation |
|
dataset: |
|
name: GSM8k (5-shot) |
|
type: gsm8k |
|
config: main |
|
split: test |
|
args: |
|
num_few_shot: 5 |
|
metrics: |
|
- type: acc |
|
value: 75.21 |
|
name: accuracy |
|
--- |
|
|
|
# NeuralMaths-Experiment-7b |
|
|
|
## Number One in GSM8K LeaderBoard! |
|
|
|
|
|
![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d71ab4089bc502ceb44d29/G4jLrTxkxE4knJAaZB3u6.png) |
|
|
|
NeuralMaths-Experiment-7b is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing): |
|
* [WizardLM/WizardMath-7B-V1.1](https://huggingface.co/WizardLM/WizardMath-7B-V1.1) |
|
* [mlabonne/NeuralDaredevil-7B](https://huggingface.co/mlabonne/NeuralDaredevil-7B) |
|
* [Kukedlc/Neural4gsm8k](https://huggingface.co/Kukedlc/Neural4gsm8k) |
|
* [Eric111/Mayo](https://huggingface.co/Eric111/Mayo) |
|
* [Kukedlc/NeuralSirKrishna-7b](https://huggingface.co/Kukedlc/NeuralSirKrishna-7b) |
|
|
|
## 🧩 Configuration |
|
|
|
```yaml |
|
models: |
|
- model: Kukedlc/NeuralSirKrishna-7b |
|
# No parameters necessary for base model |
|
- model: WizardLM/WizardMath-7B-V1.1 |
|
parameters: |
|
density: 0.66 |
|
weight: 0.2 |
|
- model: mlabonne/NeuralDaredevil-7B |
|
parameters: |
|
density: 0.55 |
|
weight: 0.2 |
|
- model: Kukedlc/Neural4gsm8k |
|
parameters: |
|
density: 0.55 |
|
weight: 0.2 |
|
- model: Eric111/Mayo |
|
parameters: |
|
density: 0.44 |
|
weight: 0.2 |
|
- model: Kukedlc/NeuralSirKrishna-7b |
|
parameters: |
|
density: 0.66 |
|
weight: 0.2 |
|
merge_method: dare_ties |
|
base_model: Kukedlc/NeuralSirKrishna-7b |
|
parameters: |
|
int8_mask: true |
|
dtype: bfloat16 |
|
``` |
|
|
|
## 💻 Usage |
|
|
|
```python |
|
!pip install -qU transformers accelerate |
|
|
|
from transformers import AutoTokenizer |
|
import transformers |
|
import torch |
|
|
|
model = "Kukedlc/NeuralMaths-Experiment-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"]) |
|
``` |