Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) NeuralMona_MoE-4x7B - GGUF - Model creator: https://huggingface.co./CultriX/ - Original model: https://huggingface.co./CultriX/NeuralMona_MoE-4x7B/ | Name | Quant method | Size | | ---- | ---- | ---- | | [NeuralMona_MoE-4x7B.Q2_K.gguf](https://huggingface.co./RichardErkhov/CultriX_-_NeuralMona_MoE-4x7B-gguf/blob/main/NeuralMona_MoE-4x7B.Q2_K.gguf) | Q2_K | 8.24GB | | [NeuralMona_MoE-4x7B.IQ3_XS.gguf](https://huggingface.co./RichardErkhov/CultriX_-_NeuralMona_MoE-4x7B-gguf/blob/main/NeuralMona_MoE-4x7B.IQ3_XS.gguf) | IQ3_XS | 9.21GB | | [NeuralMona_MoE-4x7B.IQ3_S.gguf](https://huggingface.co./RichardErkhov/CultriX_-_NeuralMona_MoE-4x7B-gguf/blob/main/NeuralMona_MoE-4x7B.IQ3_S.gguf) | IQ3_S | 9.73GB | | [NeuralMona_MoE-4x7B.Q3_K_S.gguf](https://huggingface.co./RichardErkhov/CultriX_-_NeuralMona_MoE-4x7B-gguf/blob/main/NeuralMona_MoE-4x7B.Q3_K_S.gguf) | Q3_K_S | 9.72GB | | [NeuralMona_MoE-4x7B.IQ3_M.gguf](https://huggingface.co./RichardErkhov/CultriX_-_NeuralMona_MoE-4x7B-gguf/blob/main/NeuralMona_MoE-4x7B.IQ3_M.gguf) | IQ3_M | 9.92GB | | [NeuralMona_MoE-4x7B.Q3_K.gguf](https://huggingface.co./RichardErkhov/CultriX_-_NeuralMona_MoE-4x7B-gguf/blob/main/NeuralMona_MoE-4x7B.Q3_K.gguf) | Q3_K | 10.79GB | | [NeuralMona_MoE-4x7B.Q3_K_M.gguf](https://huggingface.co./RichardErkhov/CultriX_-_NeuralMona_MoE-4x7B-gguf/blob/main/NeuralMona_MoE-4x7B.Q3_K_M.gguf) | Q3_K_M | 10.79GB | | [NeuralMona_MoE-4x7B.Q3_K_L.gguf](https://huggingface.co./RichardErkhov/CultriX_-_NeuralMona_MoE-4x7B-gguf/blob/main/NeuralMona_MoE-4x7B.Q3_K_L.gguf) | Q3_K_L | 11.68GB | | [NeuralMona_MoE-4x7B.IQ4_XS.gguf](https://huggingface.co./RichardErkhov/CultriX_-_NeuralMona_MoE-4x7B-gguf/blob/main/NeuralMona_MoE-4x7B.IQ4_XS.gguf) | IQ4_XS | 12.15GB | | [NeuralMona_MoE-4x7B.Q4_0.gguf](https://huggingface.co./RichardErkhov/CultriX_-_NeuralMona_MoE-4x7B-gguf/blob/main/NeuralMona_MoE-4x7B.Q4_0.gguf) | Q4_0 | 12.69GB | | [NeuralMona_MoE-4x7B.IQ4_NL.gguf](https://huggingface.co./RichardErkhov/CultriX_-_NeuralMona_MoE-4x7B-gguf/blob/main/NeuralMona_MoE-4x7B.IQ4_NL.gguf) | IQ4_NL | 12.81GB | | [NeuralMona_MoE-4x7B.Q4_K_S.gguf](https://huggingface.co./RichardErkhov/CultriX_-_NeuralMona_MoE-4x7B-gguf/blob/main/NeuralMona_MoE-4x7B.Q4_K_S.gguf) | Q4_K_S | 12.8GB | | [NeuralMona_MoE-4x7B.Q4_K.gguf](https://huggingface.co./RichardErkhov/CultriX_-_NeuralMona_MoE-4x7B-gguf/blob/main/NeuralMona_MoE-4x7B.Q4_K.gguf) | Q4_K | 13.61GB | | [NeuralMona_MoE-4x7B.Q4_K_M.gguf](https://huggingface.co./RichardErkhov/CultriX_-_NeuralMona_MoE-4x7B-gguf/blob/main/NeuralMona_MoE-4x7B.Q4_K_M.gguf) | Q4_K_M | 13.61GB | | [NeuralMona_MoE-4x7B.Q4_1.gguf](https://huggingface.co./RichardErkhov/CultriX_-_NeuralMona_MoE-4x7B-gguf/blob/main/NeuralMona_MoE-4x7B.Q4_1.gguf) | Q4_1 | 14.09GB | | [NeuralMona_MoE-4x7B.Q5_0.gguf](https://huggingface.co./RichardErkhov/CultriX_-_NeuralMona_MoE-4x7B-gguf/blob/main/NeuralMona_MoE-4x7B.Q5_0.gguf) | Q5_0 | 15.48GB | | [NeuralMona_MoE-4x7B.Q5_K_S.gguf](https://huggingface.co./RichardErkhov/CultriX_-_NeuralMona_MoE-4x7B-gguf/blob/main/NeuralMona_MoE-4x7B.Q5_K_S.gguf) | Q5_K_S | 15.48GB | | [NeuralMona_MoE-4x7B.Q5_K.gguf](https://huggingface.co./RichardErkhov/CultriX_-_NeuralMona_MoE-4x7B-gguf/blob/main/NeuralMona_MoE-4x7B.Q5_K.gguf) | Q5_K | 15.96GB | | [NeuralMona_MoE-4x7B.Q5_K_M.gguf](https://huggingface.co./RichardErkhov/CultriX_-_NeuralMona_MoE-4x7B-gguf/blob/main/NeuralMona_MoE-4x7B.Q5_K_M.gguf) | Q5_K_M | 15.96GB | | [NeuralMona_MoE-4x7B.Q5_1.gguf](https://huggingface.co./RichardErkhov/CultriX_-_NeuralMona_MoE-4x7B-gguf/blob/main/NeuralMona_MoE-4x7B.Q5_1.gguf) | Q5_1 | 16.88GB | | [NeuralMona_MoE-4x7B.Q6_K.gguf](https://huggingface.co./RichardErkhov/CultriX_-_NeuralMona_MoE-4x7B-gguf/blob/main/NeuralMona_MoE-4x7B.Q6_K.gguf) | Q6_K | 18.46GB | | [NeuralMona_MoE-4x7B.Q8_0.gguf](https://huggingface.co./RichardErkhov/CultriX_-_NeuralMona_MoE-4x7B-gguf/blob/main/NeuralMona_MoE-4x7B.Q8_0.gguf) | Q8_0 | 23.9GB | Original model description: --- license: apache-2.0 tags: - moe - frankenmoe - merge - mergekit - lazymergekit - CultriX/MonaTrix-v4 - mlabonne/OmniTruthyBeagle-7B-v0 - CultriX/MoNeuTrix-7B-v1 - paulml/OmniBeagleSquaredMBX-v3-7B base_model: - CultriX/MonaTrix-v4 - mlabonne/OmniTruthyBeagle-7B-v0 - CultriX/MoNeuTrix-7B-v1 - paulml/OmniBeagleSquaredMBX-v3-7B --- # NeuralMona_MoE-4x7B NeuralMona_MoE-4x7B is a Mixture of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing): * [CultriX/MonaTrix-v4](https://huggingface.co./CultriX/MonaTrix-v4) * [mlabonne/OmniTruthyBeagle-7B-v0](https://huggingface.co./mlabonne/OmniTruthyBeagle-7B-v0) * [CultriX/MoNeuTrix-7B-v1](https://huggingface.co./CultriX/MoNeuTrix-7B-v1) * [paulml/OmniBeagleSquaredMBX-v3-7B](https://huggingface.co./paulml/OmniBeagleSquaredMBX-v3-7B) ## 🧩 Configuration ```yaml base_model: CultriX/MonaTrix-v4 dtype: bfloat16 experts: - source_model: "CultriX/MonaTrix-v4" # Historical Analysis, Geopolitics, and Economic Evaluation positive_prompts: - "Historic analysis" - "Geopolitical impacts" - "Evaluate significance" - "Predict impact" - "Assess consequences" - "Discuss implications" - "Explain geopolitical" - "Analyze historical" - "Examine economic" - "Evaluate role" - "Analyze importance" - "Discuss cultural impact" - "Discuss historical" negative_prompts: - "Compose" - "Translate" - "Debate" - "Solve math" - "Analyze data" - "Forecast" - "Predict" - "Process" - "Coding" - "Programming" - "Code" - "Datascience" - "Cryptography" - source_model: "mlabonne/OmniTruthyBeagle-7B-v0" # Multilingual Communication and Cultural Insights positive_prompts: - "Describe cultural" - "Explain in language" - "Translate" - "Compare cultural differences" - "Discuss cultural impact" - "Narrate in language" - "Explain impact on culture" - "Discuss national identity" - "Describe cultural significance" - "Narrate cultural" - "Discuss folklore" negative_prompts: - "Compose" - "Debate" - "Solve math" - "Analyze data" - "Forecast" - "Predict" - "Coding" - "Programming" - "Code" - "Datascience" - "Cryptography" - source_model: "CultriX/MoNeuTrix-7B-v1" # Problem Solving, Innovation, and Creative Thinking positive_prompts: - "Devise strategy" - "Imagine society" - "Invent device" - "Design concept" - "Propose theory" - "Reason math" - "Develop strategy" - "Invent" negative_prompts: - "Translate" - "Discuss" - "Debate" - "Summarize" - "Explain" - "Detail" - "Compose" - source_model: "paulml/OmniBeagleSquaredMBX-v3-7B" # Explaining Scientific Phenomena and Principles positive_prompts: - "Explain scientific" - "Discuss impact" - "Analyze potential" - "Elucidate significance" - "Summarize findings" - "Detail explanation" negative_prompts: - "Cultural significance" - "Engage in creative writing" - "Perform subjective judgment tasks" - "Discuss cultural traditions" - "Write review" - "Design" - "Create" - "Narrate" - "Discuss" ``` ## 💻 Usage ```python !pip install -qU transformers bitsandbytes accelerate from transformers import AutoTokenizer import transformers import torch model = "CultriX/NeuralMona_MoE-4x7B" tokenizer = AutoTokenizer.from_pretrained(model) pipeline = transformers.pipeline( "text-generation", model=model, model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True}, ) messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}] prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) 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"]) ```