Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
AISE-TUDelft/ML4SE23_G1_WizardCoder-SCoT-1B-V1.0 - GGUF
This repo contains GGUF format model files for AISE-TUDelft/ML4SE23_G1_WizardCoder-SCoT-1B-V1.0.
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 |
|---|---|---|---|
| ML4SE23_G1_WizardCoder-SCoT-1B-V1.0-Q2_K.gguf | Q2_K | 0.572 GB | smallest, significant quality loss - not recommended for most purposes |
| ML4SE23_G1_WizardCoder-SCoT-1B-V1.0-Q3_K_S.gguf | Q3_K_S | 0.635 GB | very small, high quality loss |
| ML4SE23_G1_WizardCoder-SCoT-1B-V1.0-Q3_K_M.gguf | Q3_K_M | 0.719 GB | very small, high quality loss |
| ML4SE23_G1_WizardCoder-SCoT-1B-V1.0-Q3_K_L.gguf | Q3_K_L | 0.780 GB | small, substantial quality loss |
| ML4SE23_G1_WizardCoder-SCoT-1B-V1.0-Q4_0.gguf | Q4_0 | 0.784 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| ML4SE23_G1_WizardCoder-SCoT-1B-V1.0-Q4_K_S.gguf | Q4_K_S | 0.790 GB | small, greater quality loss |
| ML4SE23_G1_WizardCoder-SCoT-1B-V1.0-Q4_K_M.gguf | Q4_K_M | 0.850 GB | medium, balanced quality - recommended |
| ML4SE23_G1_WizardCoder-SCoT-1B-V1.0-Q5_0.gguf | Q5_0 | 0.924 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| ML4SE23_G1_WizardCoder-SCoT-1B-V1.0-Q5_K_S.gguf | Q5_K_S | 0.924 GB | large, low quality loss - recommended |
| ML4SE23_G1_WizardCoder-SCoT-1B-V1.0-Q5_K_M.gguf | Q5_K_M | 0.965 GB | large, very low quality loss - recommended |
| ML4SE23_G1_WizardCoder-SCoT-1B-V1.0-Q6_K.gguf | Q6_K | 1.072 GB | very large, extremely low quality loss |
| ML4SE23_G1_WizardCoder-SCoT-1B-V1.0-Q8_0.gguf | Q8_0 | 1.368 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/ML4SE23_G1_WizardCoder-SCoT-1B-V1.0-GGUF --include "ML4SE23_G1_WizardCoder-SCoT-1B-V1.0-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/ML4SE23_G1_WizardCoder-SCoT-1B-V1.0-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
- Downloads last month
- 77
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.