Hugging Face's logo

tensorblock
/
code-millenials-13b-GGUF

Transformers
GGUF
code
TensorBlock
GGUF
Eval Results
Inference Endpoints
Model card Files Community
code-millenials-13b-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
6e71b53 verified
preview code
|
raw
history blame contribute delete
5.02 kB
metadata
license: llama2
library_name: transformers
tags:
  - code
  - TensorBlock
  - GGUF
base_model: budecosystem/code-millenials-13b
model-index:
  - name: Code Millenials
    results:
      - task:
          type: text-generation
        dataset:
          name: HumanEval
          type: openai_humaneval
        metrics:
          - type: pass@1
            value: 0.7621
            name: pass@1
            verified: false
TensorBlock

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

budecosystem/code-millenials-13b - GGUF

This repo contains GGUF format model files for budecosystem/code-millenials-13b.

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
code-millenials-13b-Q2_K.gguf Q2_K 4.855 GB smallest, significant quality loss - not recommended for most purposes
code-millenials-13b-Q3_K_S.gguf Q3_K_S 5.659 GB very small, high quality loss
code-millenials-13b-Q3_K_M.gguf Q3_K_M 6.338 GB very small, high quality loss
code-millenials-13b-Q3_K_L.gguf Q3_K_L 6.930 GB small, substantial quality loss
code-millenials-13b-Q4_0.gguf Q4_0 7.366 GB legacy; small, very high quality loss - prefer using Q3_K_M
code-millenials-13b-Q4_K_S.gguf Q4_K_S 7.424 GB small, greater quality loss
code-millenials-13b-Q4_K_M.gguf Q4_K_M 7.866 GB medium, balanced quality - recommended
code-millenials-13b-Q5_0.gguf Q5_0 8.973 GB legacy; medium, balanced quality - prefer using Q4_K_M
code-millenials-13b-Q5_K_S.gguf Q5_K_S 8.973 GB large, low quality loss - recommended
code-millenials-13b-Q5_K_M.gguf Q5_K_M 9.230 GB large, very low quality loss - recommended
code-millenials-13b-Q6_K.gguf Q6_K 10.680 GB very large, extremely low quality loss
code-millenials-13b-Q8_0.gguf Q8_0 13.832 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/code-millenials-13b-GGUF --include "code-millenials-13b-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/code-millenials-13b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'