Hugging Face's logo

tensorblock
/
EEVE-Math-10.8B-GGUF

GGUF
Korean
math
TensorBlock
GGUF
Eval Results
Inference Endpoints
conversational
Model card Files Community
EEVE-Math-10.8B-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
4de90c4 verified
preview code
|
raw
history blame contribute delete
4.97 kB
metadata
base_model: kuotient/EEVE-Math-10.8B
license: cc-by-sa-4.0
language:
  - ko
tags:
  - math
  - TensorBlock
  - GGUF
datasets:
  - kuotient/orca-math-word-problems-193k-korean
model-index:
  - name: EEVE-Math-10.8B
    results:
      - task:
          type: text-generation
        dataset:
          name: gsm8k-ko
          type: gsm8k
        metrics:
          - type: pass@1
            value: 0.539
            name: pass@1
            verified: false
TensorBlock

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

kuotient/EEVE-Math-10.8B - GGUF

This repo contains GGUF format model files for kuotient/EEVE-Math-10.8B.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.

Prompt template 

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Model file specification

Filename Quant type File Size Description
EEVE-Math-10.8B-Q2_K.gguf Q2_K 4.046 GB smallest, significant quality loss - not recommended for most purposes
EEVE-Math-10.8B-Q3_K_S.gguf Q3_K_S 4.711 GB very small, high quality loss
EEVE-Math-10.8B-Q3_K_M.gguf Q3_K_M 5.242 GB very small, high quality loss
EEVE-Math-10.8B-Q3_K_L.gguf Q3_K_L 5.697 GB small, substantial quality loss
EEVE-Math-10.8B-Q4_0.gguf Q4_0 6.123 GB legacy; small, very high quality loss - prefer using Q3_K_M
EEVE-Math-10.8B-Q4_K_S.gguf Q4_K_S 6.169 GB small, greater quality loss
EEVE-Math-10.8B-Q4_K_M.gguf Q4_K_M 6.513 GB medium, balanced quality - recommended
EEVE-Math-10.8B-Q5_0.gguf Q5_0 7.453 GB legacy; medium, balanced quality - prefer using Q4_K_M
EEVE-Math-10.8B-Q5_K_S.gguf Q5_K_S 7.453 GB large, low quality loss - recommended
EEVE-Math-10.8B-Q5_K_M.gguf Q5_K_M 7.653 GB large, very low quality loss - recommended
EEVE-Math-10.8B-Q6_K.gguf Q6_K 8.866 GB very large, extremely low quality loss
EEVE-Math-10.8B-Q8_0.gguf Q8_0 11.482 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/EEVE-Math-10.8B-GGUF --include "EEVE-Math-10.8B-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/EEVE-Math-10.8B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'