Hugging Face's logo

tensorblock
/
gemma-2-9b-it-tr-GGUF

Text Generation
Transformers
GGUF
Turkish
TensorBlock
GGUF
Eval Results
Inference Endpoints
conversational
Model card Files Community
gemma-2-9b-it-tr-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
de82ed2 verified
preview code
|
raw
history blame contribute delete
5.4 kB
metadata
library_name: transformers
license: gemma
language:
  - tr
base_model: neuralwork/gemma-2-9b-it-tr
pipeline_tag: text-generation
tags:
  - TensorBlock
  - GGUF
model-index:
  - name: neuralwork/gemma-2-9b-it-tr
    results:
      - task:
          type: multiple-choice
        dataset:
          name: MMLU_TR_V0.2
          type: multiple-choice
        metrics:
          - type: 5-shot
            value: 0.6117
            name: 5-shot
            verified: true
          - type: 0-shot
            value: 0.5583
            name: 0-shot
            verified: true
          - type: 25-shot
            value: 0.564
            name: 25-shot
            verified: true
          - type: 10-shot
            value: 0.5646
            name: 10-shot
            verified: true
          - type: 5-shot
            value: 0.6211
            name: 5-shot
            verified: true
          - type: 5-shot
            value: 0.6209
            name: 5-shot
            verified: true
TensorBlock

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

neuralwork/gemma-2-9b-it-tr - GGUF

This repo contains GGUF format model files for neuralwork/gemma-2-9b-it-tr.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4823.

Prompt template 

<bos><start_of_turn>user
{prompt}<end_of_turn>
<start_of_turn>model

Model file specification

Filename Quant type File Size Description
gemma-2-9b-it-tr-Q2_K.gguf Q2_K 3.805 GB smallest, significant quality loss - not recommended for most purposes
gemma-2-9b-it-tr-Q3_K_S.gguf Q3_K_S 4.338 GB very small, high quality loss
gemma-2-9b-it-tr-Q3_K_M.gguf Q3_K_M 4.762 GB very small, high quality loss
gemma-2-9b-it-tr-Q3_K_L.gguf Q3_K_L 5.132 GB small, substantial quality loss
gemma-2-9b-it-tr-Q4_0.gguf Q4_0 5.443 GB legacy; small, very high quality loss - prefer using Q3_K_M
gemma-2-9b-it-tr-Q4_K_S.gguf Q4_K_S 5.479 GB small, greater quality loss
gemma-2-9b-it-tr-Q4_K_M.gguf Q4_K_M 5.761 GB medium, balanced quality - recommended
gemma-2-9b-it-tr-Q5_0.gguf Q5_0 6.484 GB legacy; medium, balanced quality - prefer using Q4_K_M
gemma-2-9b-it-tr-Q5_K_S.gguf Q5_K_S 6.484 GB large, low quality loss - recommended
gemma-2-9b-it-tr-Q5_K_M.gguf Q5_K_M 6.647 GB large, very low quality loss - recommended
gemma-2-9b-it-tr-Q6_K.gguf Q6_K 7.589 GB very large, extremely low quality loss
gemma-2-9b-it-tr-Q8_0.gguf Q8_0 9.827 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/gemma-2-9b-it-tr-GGUF --include "gemma-2-9b-it-tr-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/gemma-2-9b-it-tr-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'