--- license: apache-2.0 datasets: - Severian/Biomimicry pipeline_tag: text-generation tags: - science - design - biomimicry - nature - ecology - TensorBlock - GGUF base_model: Severian/ANIMA-Cognitive-Mistral-v1 --- <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p style="margin-top: 0.5em; margin-bottom: 0em;"> Feedback and support: TensorBlock's <a href="https://x.com/tensorblock_aoi">Twitter/X</a>, <a href="https://t.me/TensorBlock">Telegram Group</a> and <a href="https://x.com/tensorblock_aoi">Discord server</a> </p> </div> </div> ## Severian/ANIMA-Cognitive-Mistral-v1 - GGUF This repo contains GGUF format model files for [Severian/ANIMA-Cognitive-Mistral-v1](https://huggingface.co/Severian/ANIMA-Cognitive-Mistral-v1). The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4242](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d). <div style="text-align: left; margin: 20px 0;"> <a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;"> Run them on the TensorBlock client using your local machine ↗ </a> </div> ## Prompt template ``` ``` ## Model file specification | Filename | Quant type | File Size | Description | | -------- | ---------- | --------- | ----------- | | [ANIMA-Cognitive-Mistral-v1-Q2_K.gguf](https://huggingface.co/tensorblock/ANIMA-Cognitive-Mistral-v1-GGUF/blob/main/ANIMA-Cognitive-Mistral-v1-Q2_K.gguf) | Q2_K | 2.719 GB | smallest, significant quality loss - not recommended for most purposes | | [ANIMA-Cognitive-Mistral-v1-Q3_K_S.gguf](https://huggingface.co/tensorblock/ANIMA-Cognitive-Mistral-v1-GGUF/blob/main/ANIMA-Cognitive-Mistral-v1-Q3_K_S.gguf) | Q3_K_S | 3.165 GB | very small, high quality loss | | [ANIMA-Cognitive-Mistral-v1-Q3_K_M.gguf](https://huggingface.co/tensorblock/ANIMA-Cognitive-Mistral-v1-GGUF/blob/main/ANIMA-Cognitive-Mistral-v1-Q3_K_M.gguf) | Q3_K_M | 3.519 GB | very small, high quality loss | | [ANIMA-Cognitive-Mistral-v1-Q3_K_L.gguf](https://huggingface.co/tensorblock/ANIMA-Cognitive-Mistral-v1-GGUF/blob/main/ANIMA-Cognitive-Mistral-v1-Q3_K_L.gguf) | Q3_K_L | 3.822 GB | small, substantial quality loss | | [ANIMA-Cognitive-Mistral-v1-Q4_0.gguf](https://huggingface.co/tensorblock/ANIMA-Cognitive-Mistral-v1-GGUF/blob/main/ANIMA-Cognitive-Mistral-v1-Q4_0.gguf) | Q4_0 | 4.109 GB | legacy; small, very high quality loss - prefer using Q3_K_M | | [ANIMA-Cognitive-Mistral-v1-Q4_K_S.gguf](https://huggingface.co/tensorblock/ANIMA-Cognitive-Mistral-v1-GGUF/blob/main/ANIMA-Cognitive-Mistral-v1-Q4_K_S.gguf) | Q4_K_S | 4.140 GB | small, greater quality loss | | [ANIMA-Cognitive-Mistral-v1-Q4_K_M.gguf](https://huggingface.co/tensorblock/ANIMA-Cognitive-Mistral-v1-GGUF/blob/main/ANIMA-Cognitive-Mistral-v1-Q4_K_M.gguf) | Q4_K_M | 4.368 GB | medium, balanced quality - recommended | | [ANIMA-Cognitive-Mistral-v1-Q5_0.gguf](https://huggingface.co/tensorblock/ANIMA-Cognitive-Mistral-v1-GGUF/blob/main/ANIMA-Cognitive-Mistral-v1-Q5_0.gguf) | Q5_0 | 4.998 GB | legacy; medium, balanced quality - prefer using Q4_K_M | | [ANIMA-Cognitive-Mistral-v1-Q5_K_S.gguf](https://huggingface.co/tensorblock/ANIMA-Cognitive-Mistral-v1-GGUF/blob/main/ANIMA-Cognitive-Mistral-v1-Q5_K_S.gguf) | Q5_K_S | 4.998 GB | large, low quality loss - recommended | | [ANIMA-Cognitive-Mistral-v1-Q5_K_M.gguf](https://huggingface.co/tensorblock/ANIMA-Cognitive-Mistral-v1-GGUF/blob/main/ANIMA-Cognitive-Mistral-v1-Q5_K_M.gguf) | Q5_K_M | 5.131 GB | large, very low quality loss - recommended | | [ANIMA-Cognitive-Mistral-v1-Q6_K.gguf](https://huggingface.co/tensorblock/ANIMA-Cognitive-Mistral-v1-GGUF/blob/main/ANIMA-Cognitive-Mistral-v1-Q6_K.gguf) | Q6_K | 5.942 GB | very large, extremely low quality loss | | [ANIMA-Cognitive-Mistral-v1-Q8_0.gguf](https://huggingface.co/tensorblock/ANIMA-Cognitive-Mistral-v1-GGUF/blob/main/ANIMA-Cognitive-Mistral-v1-Q8_0.gguf) | Q8_0 | 7.696 GB | very large, extremely low quality loss - not recommended | ## Downloading instruction ### Command line Firstly, install Huggingface Client ```shell pip install -U "huggingface_hub[cli]" ``` Then, downoad the individual model file the a local directory ```shell huggingface-cli download tensorblock/ANIMA-Cognitive-Mistral-v1-GGUF --include "ANIMA-Cognitive-Mistral-v1-Q2_K.gguf" --local-dir MY_LOCAL_DIR ``` If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try: ```shell huggingface-cli download tensorblock/ANIMA-Cognitive-Mistral-v1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf' ```