--- tags: - merge - mergekit - lazymergekit - yam-peleg/Experiment26-7B - Kukedlc/NeuralSirKrishna-7b - automerger/YamShadow-7B base_model: - yam-peleg/Experiment26-7B - Kukedlc/NeuralSirKrishna-7b - automerger/YamShadow-7B license: apache-2.0 --- # NeuralContamination-7B-ties ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d71ab4089bc502ceb44d29/PyDI8KAlRmzKQ8sEFORQ9.png) NeuralContamination-7B-ties is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing): * [yam-peleg/Experiment26-7B](https://huggingface.co/yam-peleg/Experiment26-7B) * [Kukedlc/NeuralSirKrishna-7b](https://huggingface.co/Kukedlc/NeuralSirKrishna-7b) * [automerger/YamShadow-7B](https://huggingface.co/automerger/YamShadow-7B) ## 🧩 Configuration ```yaml models: - model: yam-peleg/Experiment26-7B parameters: density: [1, 0.7, 0.1] # density gradient weight: 1.0 - model: Kukedlc/NeuralSirKrishna-7b parameters: density: 0.5 weight: [0, 0.3, 0.7, 1] # weight gradient - model: automerger/YamShadow-7B parameters: density: 0.33 weight: - filter: mlp value: 0.5 - value: 0 merge_method: ties base_model: liminerity/M7-7b parameters: normalize: true int8_mask: true dtype: bfloat16 ``` ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "Kukedlc/NeuralContamination-7B-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"]) ``` ## Genetic ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d71ab4089bc502ceb44d29/GrB1JfyS2lm_IeM05QMp5.png)