--- base_model: - powermove72/Shark-1 - eren23/OGNO-7b-dpo-truthful tags: - merge - mergekit - lazymergekit - powermove72/Shark-1 - eren23/OGNO-7b-dpo-truthful --- # Shark-1-Ogno-9b-passthrough Shark-1-Ogno-9b-passthrough is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing): * [powermove72/Shark-1](https://huggingface.co/powermove72/Shark-1) * [eren23/OGNO-7b-dpo-truthful](https://huggingface.co/eren23/OGNO-7b-dpo-truthful) ## 🧩 Configuration ```yaml slices: - sources: - model: powermove72/Shark-1 layer_range: [0, 16] - sources: - model: eren23/OGNO-7b-dpo-truthful layer_range: [8, 32] merge_method: passthrough tokenizer_source: union dtype: float16 ``` ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "powermove72/Shark-1-Ogno-9b-passthrough" 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"]) ```