metadata
library_name: transformers
tags:
- TensorBlock
- GGUF
base_model: hyper-accel/tiny-random-starcoder2
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
hyper-accel/tiny-random-starcoder2 - GGUF
This repo contains GGUF format model files for hyper-accel/tiny-random-starcoder2.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4882.
Prompt template
Unable to determine prompt format automatically. Please check the original model repository for the correct prompt format.
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| tiny-random-starcoder2-Q2_K.gguf | Q2_K | 0.068 GB | smallest, significant quality loss - not recommended for most purposes |
| tiny-random-starcoder2-Q3_K_S.gguf | Q3_K_S | 0.074 GB | very small, high quality loss |
| tiny-random-starcoder2-Q3_K_M.gguf | Q3_K_M | 0.076 GB | very small, high quality loss |
| tiny-random-starcoder2-Q3_K_L.gguf | Q3_K_L | 0.077 GB | small, substantial quality loss |
| tiny-random-starcoder2-Q4_0.gguf | Q4_0 | 0.084 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| tiny-random-starcoder2-Q4_K_S.gguf | Q4_K_S | 0.084 GB | small, greater quality loss |
| tiny-random-starcoder2-Q4_K_M.gguf | Q4_K_M | 0.085 GB | medium, balanced quality - recommended |
| tiny-random-starcoder2-Q5_0.gguf | Q5_0 | 0.093 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| tiny-random-starcoder2-Q5_K_S.gguf | Q5_K_S | 0.093 GB | large, low quality loss - recommended |
| tiny-random-starcoder2-Q5_K_M.gguf | Q5_K_M | 0.093 GB | large, very low quality loss - recommended |
| tiny-random-starcoder2-Q6_K.gguf | Q6_K | 0.102 GB | very large, extremely low quality loss |
| tiny-random-starcoder2-Q8_0.gguf | Q8_0 | 0.132 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/tiny-random-starcoder2-GGUF --include "tiny-random-starcoder2-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/tiny-random-starcoder2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'