Deepseek-math-7B-arithmetic-mk-v2

Deepseek-math-7B-arithmetic-mk-v2

Deepseek-math-7B-arithmetic-mk-v2 is a merge of the following models using LazyMergekit:

• deepseek-ai/deepseek-math-7b-rl
• sudhanshu746/deepseek-7b-instruct-matho-finetune

🧩 Configuration

models:
  - model: deepseek-ai/deepseek-math-7b-rl
    parameters:
      weight: 1
  - model: sudhanshu746/deepseek-7b-instruct-matho-finetune
    parameters:
      weight: 1
merge_method: task_arithmetic
base_model: deepseek-ai/deepseek-math-7b-instruct
parameters:
  normalize: true
  int8_mask: true
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "sudhanshu746/Deepseek-math-7B-arithmetic-mk-v2"
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"])