Zelknight463_-_deepseek-coder-ties-8bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

deepseek-coder-ties - bnb 8bits

• Model creator: https://huggingface.co/Zelknight463/
• Original model: https://huggingface.co/Zelknight463/deepseek-coder-ties/

Original model description:

base_model:

• deepseek-ai/deepseek-coder-6.7b-instruct
• m-a-p/OpenCodeInterpreter-DS-6.7B tags:
• merge
• mergekit
• lazymergekit
• deepseek-ai/deepseek-coder-6.7b-instruct
• m-a-p/OpenCodeInterpreter-DS-6.7B

---

deepseek-coder-ties

deepseek-coder-ties is a merge of the following models using LazyMergekit:

• deepseek-ai/deepseek-coder-6.7b-instruct
• m-a-p/OpenCodeInterpreter-DS-6.7B

🧩 Configuration

models:
  - model: deepseek-ai/deepseek-coder-6.7b-instruct
    parameters:
      density: [1, 0.7, 0.1] # density gradient
      weight: 1.0
  - model: m-a-p/OpenCodeInterpreter-DS-6.7B
    parameters:
      density: 0.5
      weight: [0, 0.3, 0.7, 1] # weight gradient
merge_method: ties
base_model: deepseek-ai/deepseek-coder-6.7b-base
parameters:
  normalize: true
  int8_mask: true
dtype: float16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Zelknight463/deepseek-coder-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"])