metadata
library_name: transformers
license: apache-2.0
datasets:
- recogna-nlp/ultra-alpaca-ptbr
language:
- pt
base_model: Felladrin/Minueza-2-96M-Instruct-Variant-02
tags:
- llama-factory
- TensorBlock
- GGUF
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
Felladrin/Minueza-2-96M-Instruct-Variant-02 - GGUF
This repo contains GGUF format model files for Felladrin/Minueza-2-96M-Instruct-Variant-02.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b5165.
Our projects
| Awesome MCP Servers | TensorBlock Studio |
|---|---|
 |
 |
| A comprehensive collection of Model Context Protocol (MCP) servers. | A lightweight, open, and extensible multi-LLM interaction studio. |
| 👀 See what we built 👀 | 👀 See what we built 👀 |
Prompt template
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| Minueza-2-96M-Instruct-Variant-02-Q2_K.gguf | Q2_K | 0.066 GB | smallest, significant quality loss - not recommended for most purposes |
| Minueza-2-96M-Instruct-Variant-02-Q3_K_S.gguf | Q3_K_S | 0.066 GB | very small, high quality loss |
| Minueza-2-96M-Instruct-Variant-02-Q3_K_M.gguf | Q3_K_M | 0.068 GB | very small, high quality loss |
| Minueza-2-96M-Instruct-Variant-02-Q3_K_L.gguf | Q3_K_L | 0.069 GB | small, substantial quality loss |
| Minueza-2-96M-Instruct-Variant-02-Q4_0.gguf | Q4_0 | 0.066 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| Minueza-2-96M-Instruct-Variant-02-Q4_K_S.gguf | Q4_K_S | 0.075 GB | small, greater quality loss |
| Minueza-2-96M-Instruct-Variant-02-Q4_K_M.gguf | Q4_K_M | 0.078 GB | medium, balanced quality - recommended |
| Minueza-2-96M-Instruct-Variant-02-Q5_0.gguf | Q5_0 | 0.075 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| Minueza-2-96M-Instruct-Variant-02-Q5_K_S.gguf | Q5_K_S | 0.079 GB | large, low quality loss - recommended |
| Minueza-2-96M-Instruct-Variant-02-Q5_K_M.gguf | Q5_K_M | 0.082 GB | large, very low quality loss - recommended |
| Minueza-2-96M-Instruct-Variant-02-Q6_K.gguf | Q6_K | 0.103 GB | very large, extremely low quality loss |
| Minueza-2-96M-Instruct-Variant-02-Q8_0.gguf | Q8_0 | 0.103 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/Felladrin_Minueza-2-96M-Instruct-Variant-02-GGUF --include "Minueza-2-96M-Instruct-Variant-02-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/Felladrin_Minueza-2-96M-Instruct-Variant-02-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'