README.md

---
base_model:
- deepseek-ai/deepseek-llm-7b-base
- deepseek-ai/deepseek-coder-7b-base-v1.5
tags:
- merge
- mergekit
- lazymergekit
- deepseek-ai/deepseek-llm-7b-base
- deepseek-ai/deepseek-coder-7b-base-v1.5
---

# SeekDeep-CodeLM-7B-Base-Ties

SeekDeep-CodeLM-7B-Base-Ties is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [deepseek-ai/deepseek-llm-7b-base](https://huggingface.co/deepseek-ai/deepseek-llm-7b-base)
* [deepseek-ai/deepseek-coder-7b-base-v1.5](https://huggingface.co/deepseek-ai/deepseek-coder-7b-base-v1.5)

## 🧩 Configuration

```yaml
models:

  - model: deepseek-ai/deepseek-llm-7b-base

    parameters:

      weight: 1

      density: 1

  - model: deepseek-ai/deepseek-coder-7b-base-v1.5

    parameters:

      weight: 1

      density: 1

merge_method: ties

base_model: deepseek-ai/deepseek-llm-7b-base

parameters:

  weight: 1

  density: 1

  normalize: true

  int8_mask: true

dtype: bfloat16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "JoPmt/SeekDeep-CodeLM-7B-Base-Ties"
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"])
```