license: apache-2.0
base_model:
- Qwen/Qwen2.5-14B-Instruct
- cognitivecomputations/Dolphin3.0-R1-Qwen-14B
tags: - merge
- mergekit
- lazymergekit
- Qwen/Qwen2.5-14B-Instruct
- cognitivecomputations/Dolphin3.0-R1-Qwen-14B
My-Uncensored-14B
My-Uncensored-14B is a merge of the following models using LazyMergekit:
🧩 Configuration
models:
- model: Qwen/Qwen2.5-14B-Instruct
parameters:
weight: 0.5
- model: cognitivecomputations/Dolphin3.0-R1-Qwen-14B
parameters:
weight: 0.5
merge_method: linear
dtype: float16
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "DismasK/My-Uncensored-14B"
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"])