Kukedlc/SomeModelsMerge-7b

1---2tags:3- merge4- mergekit5- lazymergekit6- liminerity/M7-7b7- Kukedlc/NeuralSirKrishna-7b8- Kukedlc/MyModelsMerge-7b9- AurelPx/Percival_01-7b-slerp10- MatthieuJ/Jason1903_SLERP11- MTSAIR/multi_verse_model12- Gille/StrangeMerges_30-7B-slerp13- chihoonlee10/T3Q-Mistral-Orca-Math-DPO14- yam-peleg/Experiment28-7B15- mlabonne/UltraMerge-7B16base_model:17- liminerity/M7-7b18- Kukedlc/NeuralSirKrishna-7b19- Kukedlc/MyModelsMerge-7b20- AurelPx/Percival_01-7b-slerp21- MatthieuJ/Jason1903_SLERP22- MTSAIR/multi_verse_model23- Gille/StrangeMerges_30-7B-slerp24- chihoonlee10/T3Q-Mistral-Orca-Math-DPO25- yam-peleg/Experiment28-7B26- mlabonne/UltraMerge-7B27---28 29# SomeModelsMerge-7b30 31SomeModelsMerge-7b is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):32* [liminerity/M7-7b](https://huggingface.co/liminerity/M7-7b)33* [Kukedlc/NeuralSirKrishna-7b](https://huggingface.co/Kukedlc/NeuralSirKrishna-7b)34* [Kukedlc/MyModelsMerge-7b](https://huggingface.co/Kukedlc/MyModelsMerge-7b)35* [AurelPx/Percival_01-7b-slerp](https://huggingface.co/AurelPx/Percival_01-7b-slerp)36* [MatthieuJ/Jason1903_SLERP](https://huggingface.co/MatthieuJ/Jason1903_SLERP)37* [MTSAIR/multi_verse_model](https://huggingface.co/MTSAIR/multi_verse_model)38* [Gille/StrangeMerges_30-7B-slerp](https://huggingface.co/Gille/StrangeMerges_30-7B-slerp)39* [chihoonlee10/T3Q-Mistral-Orca-Math-DPO](https://huggingface.co/chihoonlee10/T3Q-Mistral-Orca-Math-DPO)40* [yam-peleg/Experiment28-7B](https://huggingface.co/yam-peleg/Experiment28-7B)41* [mlabonne/UltraMerge-7B](https://huggingface.co/mlabonne/UltraMerge-7B)42 43## 🧩 Configuration44 45```yaml46models:47  - model: liminerity/M7-7b48    # no parameters necessary for base model49  - model: liminerity/M7-7b50    parameters:51      weight: 0.252      density: 0.8853  - model: Kukedlc/NeuralSirKrishna-7b54    parameters:55      weight: 0.156      density: 0.6657  - model: Kukedlc/MyModelsMerge-7b58    parameters:59      weight: 0.160      density: 0.6661  - model: AurelPx/Percival_01-7b-slerp62    parameters:63      weight: 0.164      density: 0.3365  - model: MatthieuJ/Jason1903_SLERP66    parameters:67      weight: 0.168      density: 0.3369  - model: MTSAIR/multi_verse_model70    parameters:71      weight: 0.172      density: 0.6673  - model: Gille/StrangeMerges_30-7B-slerp74    parameters:75      weight: 0.176      density: 0.5577  - model: chihoonlee10/T3Q-Mistral-Orca-Math-DPO78    parameters:79      weight: 0.180      density: 0.2281  - model: yam-peleg/Experiment28-7B82    parameters:83      weight: 0.184      density: 0.4485  - model: mlabonne/UltraMerge-7B86    parameters:87      weight: 0.188      density: 0.7789merge_method: dare_ties90base_model: liminerity/M7-7b91 92parameters:93  int8_mask: true94  normalize: true95dtype: bfloat1696```97 98## 💻 Usage99 100```python101!pip install -qU transformers accelerate102 103from transformers import AutoTokenizer104import transformers105import torch106 107model = "Kukedlc/SomeModelsMerge-7b"108messages = [{"role": "user", "content": "What is a large language model?"}]109 110tokenizer = AutoTokenizer.from_pretrained(model)111prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)112pipeline = transformers.pipeline(113    "text-generation",114    model=model,115    torch_dtype=torch.float16,116    device_map="auto",117)118 119outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)120print(outputs[0]["generated_text"])121```