README.md

metadata

license: apache-2.0
tags:
  - merge
  - mergekit
  - lazymergekit
  - VortexHunter23/LeoPard-Coder-UI-0.1
  - VortexHunter23/LeoPARD-Coder-0.8.2-bfloat

LeoPARD-Coder-0.8.5-pt2-ui

LeoPARD-Coder-0.8.5-pt2-ui is a merge of the following models using LazyMergekit:

• VortexHunter23/LeoPard-Coder-UI-0.1
• VortexHunter23/LeoPARD-Coder-0.8.2-bfloat

🧩 Configuration

models:
  - model: VortexHunter23/LeoPard-Coder-UI-0.1
  - model: VortexHunter23/LeoPARD-Coder-0.8.2-bfloat
base_model: nvidia/OpenReasoning-Nemotron-14B
merge_method: model_stock
parameters:
  normalize: true
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "VortexHunter23/LeoPARD-Coder-0.8.5-pt2-ui"

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"])