metadata
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! 🏆
NeuralMaths-Experiment-7b is a merge of the following models using LazyMergekit:
- WizardLM/WizardMath-7B-V1.1
- mlabonne/NeuralDaredevil-7B
- Kukedlc/Neural4gsm8k
- Eric111/Mayo
- Kukedlc/NeuralSirKrishna-7b
🧩 Configuration
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
!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"])