metadata
datasets:
- bigcode/starcoderdata
language:
- code
tags:
- causal-lm
- TensorBlock
- GGUF
license: apache-2.0
base_model: stabilityai/stablecode-completion-alpha-3b-4k
model-index:
- name: stabilityai/stablecode-completion-alpha-3b-4k
results:
- task:
type: text-generation
dataset:
name: HumanEval
type: openai_humaneval
metrics:
- type: pass@1
value: 0.1768
name: pass@1
verified: false
- type: pass@10
value: 0.2701
name: pass@10
verified: false
stabilityai/stablecode-completion-alpha-3b-4k - GGUF
This repo contains GGUF format model files for stabilityai/stablecode-completion-alpha-3b-4k.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
Our projects
| Forge | |
|---|---|
|
|
| An OpenAI-compatible multi-provider routing layer. | |
| 🚀 Try it now! 🚀 | |
| 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 👀 |
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| stablecode-completion-alpha-3b-4k-Q2_K.gguf | Q2_K | 1.008 GB | smallest, significant quality loss - not recommended for most purposes |
| stablecode-completion-alpha-3b-4k-Q3_K_S.gguf | Q3_K_S | 1.159 GB | very small, high quality loss |
| stablecode-completion-alpha-3b-4k-Q3_K_M.gguf | Q3_K_M | 1.373 GB | very small, high quality loss |
| stablecode-completion-alpha-3b-4k-Q3_K_L.gguf | Q3_K_L | 1.489 GB | small, substantial quality loss |
| stablecode-completion-alpha-3b-4k-Q4_0.gguf | Q4_0 | 1.486 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| stablecode-completion-alpha-3b-4k-Q4_K_S.gguf | Q4_K_S | 1.498 GB | small, greater quality loss |
| stablecode-completion-alpha-3b-4k-Q4_K_M.gguf | Q4_K_M | 1.660 GB | medium, balanced quality - recommended |
| stablecode-completion-alpha-3b-4k-Q5_0.gguf | Q5_0 | 1.794 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| stablecode-completion-alpha-3b-4k-Q5_K_S.gguf | Q5_K_S | 1.794 GB | large, low quality loss - recommended |
| stablecode-completion-alpha-3b-4k-Q5_K_M.gguf | Q5_K_M | 1.923 GB | large, very low quality loss - recommended |
| stablecode-completion-alpha-3b-4k-Q6_K.gguf | Q6_K | 2.120 GB | very large, extremely low quality loss |
| stablecode-completion-alpha-3b-4k-Q8_0.gguf | Q8_0 | 2.745 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/stablecode-completion-alpha-3b-4k-GGUF --include "stablecode-completion-alpha-3b-4k-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/stablecode-completion-alpha-3b-4k-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'