metadata
base_model: LeroyDyer/Mixtral_AI_Cyber_2.0
library_name: transformers
tags:
- mergekit
- merge
- 128k_Context
- chemistry
- biology
- music
- code
- medical
- text-generation-inference
- Cyber-Series
- TensorBlock
- GGUF
previous_Merges:
- rvv-karma/BASH-Coder-Mistral-7B
- Locutusque/Hercules-3.1-Mistral-7B
- KoboldAI/Mistral-7B-Erebus-v3 - NSFW
- Locutusque/Hyperion-2.1-Mistral-7B
- Severian/Nexus-IKM-Mistral-7B-Pytorch
- NousResearch/Hermes-2-Pro-Mistral-7B
- mistralai/Mistral-7B-Instruct-v0.2
- Nitral-AI/ProdigyXBioMistral_7B
- Nitral-AI/Infinite-Mika-7b
- Nous-Yarn-Mistral-7b-128k
- yanismiraoui/Yarn-Mistral-7b-128k-sharded
license: apache-2.0
language:
- en
metrics:
- accuracy
- brier_score
- code_eval
pipeline_tag: text-generation
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
LeroyDyer/Mixtral_AI_Cyber_2.0 - GGUF
This repo contains GGUF format model files for LeroyDyer/Mixtral_AI_Cyber_2.0.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.
Prompt template
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| Mixtral_AI_Cyber_2.0-Q2_K.gguf | Q2_K | 2.719 GB | smallest, significant quality loss - not recommended for most purposes |
| Mixtral_AI_Cyber_2.0-Q3_K_S.gguf | Q3_K_S | 3.165 GB | very small, high quality loss |
| Mixtral_AI_Cyber_2.0-Q3_K_M.gguf | Q3_K_M | 3.519 GB | very small, high quality loss |
| Mixtral_AI_Cyber_2.0-Q3_K_L.gguf | Q3_K_L | 3.822 GB | small, substantial quality loss |
| Mixtral_AI_Cyber_2.0-Q4_0.gguf | Q4_0 | 4.109 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| Mixtral_AI_Cyber_2.0-Q4_K_S.gguf | Q4_K_S | 4.140 GB | small, greater quality loss |
| Mixtral_AI_Cyber_2.0-Q4_K_M.gguf | Q4_K_M | 4.368 GB | medium, balanced quality - recommended |
| Mixtral_AI_Cyber_2.0-Q5_0.gguf | Q5_0 | 4.998 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| Mixtral_AI_Cyber_2.0-Q5_K_S.gguf | Q5_K_S | 4.998 GB | large, low quality loss - recommended |
| Mixtral_AI_Cyber_2.0-Q5_K_M.gguf | Q5_K_M | 5.131 GB | large, very low quality loss - recommended |
| Mixtral_AI_Cyber_2.0-Q6_K.gguf | Q6_K | 5.942 GB | very large, extremely low quality loss |
| Mixtral_AI_Cyber_2.0-Q8_0.gguf | Q8_0 | 7.696 GB | very large, extremely low quality loss - not recommended |
Downloading instruction
Command line
Firstly, install Huggingface Client
pip install -U "huggingface_hub[cli]"
Then, downoad the individual model file the a local directory
huggingface-cli download tensorblock/Mixtral_AI_Cyber_2.0-GGUF --include "Mixtral_AI_Cyber_2.0-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:
huggingface-cli download tensorblock/Mixtral_AI_Cyber_2.0-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'