Hugging Face's logo

tensorblock
/
tiny_starcoder_py-GGUF

Text Generation
Transformers
GGUF
code
TensorBlock
GGUF
Eval Results
Inference Endpoints
Model card Files Community
tiny_starcoder_py-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
4a00bac verified
preview code
|
raw
history blame
4.77 kB
metadata
pipeline_tag: text-generation
inference: true
widget:
  - text: 'def print_hello_world():'
    example_title: Hello world
    group: Python
license: bigcode-openrail-m
datasets:
  - bigcode/the-stack-dedup
metrics:
  - code_eval
library_name: transformers
tags:
  - code
  - TensorBlock
  - GGUF
base_model: bigcode/tiny_starcoder_py
model-index:
  - name: Tiny-StarCoder-Py
    results:
      - task:
          type: text-generation
        dataset:
          name: HumanEval
          type: openai_humaneval
        metrics:
          - type: pass@1
            value: 7.84%
            name: pass@1
            verified: false
TensorBlock

Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server

bigcode/tiny_starcoder_py - GGUF

This repo contains GGUF format model files for bigcode/tiny_starcoder_py.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

Prompt template

Model file specification

Filename Quant type File Size Description
tiny_starcoder_py-Q2_K.gguf Q2_K 0.097 GB smallest, significant quality loss - not recommended for most purposes
tiny_starcoder_py-Q3_K_S.gguf Q3_K_S 0.103 GB very small, high quality loss
tiny_starcoder_py-Q3_K_M.gguf Q3_K_M 0.112 GB very small, high quality loss
tiny_starcoder_py-Q3_K_L.gguf Q3_K_L 0.118 GB small, substantial quality loss
tiny_starcoder_py-Q4_0.gguf Q4_0 0.117 GB legacy; small, very high quality loss - prefer using Q3_K_M
tiny_starcoder_py-Q4_K_S.gguf Q4_K_S 0.118 GB small, greater quality loss
tiny_starcoder_py-Q4_K_M.gguf Q4_K_M 0.125 GB medium, balanced quality - recommended
tiny_starcoder_py-Q5_0.gguf Q5_0 0.131 GB legacy; medium, balanced quality - prefer using Q4_K_M
tiny_starcoder_py-Q5_K_S.gguf Q5_K_S 0.131 GB large, low quality loss - recommended
tiny_starcoder_py-Q5_K_M.gguf Q5_K_M 0.136 GB large, very low quality loss - recommended
tiny_starcoder_py-Q6_K.gguf Q6_K 0.146 GB very large, extremely low quality loss
tiny_starcoder_py-Q8_0.gguf Q8_0 0.182 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_starcoder_py-GGUF --include "tiny_starcoder_py-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_starcoder_py-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'