Hugging Face's logo

tensorblock
/
gemma-2b-openhermes-GGUF

Text Generation
Transformers
GGUF
English
Generated from Trainer
axolotl
gemma
instruct
finetune
chatml
gpt4
synthetic data
distillation
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
gemma-2b-openhermes-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
1d6f167 verified
preview code
|
raw
history blame
5.09 kB
metadata
license: cc-by-nc-4.0
base_model: abideen/gemma-2b-openhermes
tags:
  - generated_from_trainer
  - axolotl
  - gemma
  - instruct
  - finetune
  - chatml
  - gpt4
  - synthetic data
  - distillation
  - TensorBlock
  - GGUF
datasets:
  - mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha
language:
  - en
library_name: transformers
pipeline_tag: text-generation
model-index:
  - name: gemma-2b-openhermes
    results: []
TensorBlock

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

abideen/gemma-2b-openhermes - GGUF

This repo contains GGUF format model files for abideen/gemma-2b-openhermes.

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

Prompt template 

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

Model file specification

Filename Quant type File Size Description
gemma-2b-openhermes-Q2_K.gguf Q2_K 1.158 GB smallest, significant quality loss - not recommended for most purposes
gemma-2b-openhermes-Q3_K_S.gguf Q3_K_S 1.288 GB very small, high quality loss
gemma-2b-openhermes-Q3_K_M.gguf Q3_K_M 1.384 GB very small, high quality loss
gemma-2b-openhermes-Q3_K_L.gguf Q3_K_L 1.466 GB small, substantial quality loss
gemma-2b-openhermes-Q4_0.gguf Q4_0 1.551 GB legacy; small, very high quality loss - prefer using Q3_K_M
gemma-2b-openhermes-Q4_K_S.gguf Q4_K_S 1.560 GB small, greater quality loss
gemma-2b-openhermes-Q4_K_M.gguf Q4_K_M 1.630 GB medium, balanced quality - recommended
gemma-2b-openhermes-Q5_0.gguf Q5_0 1.799 GB legacy; medium, balanced quality - prefer using Q4_K_M
gemma-2b-openhermes-Q5_K_S.gguf Q5_K_S 1.799 GB large, low quality loss - recommended
gemma-2b-openhermes-Q5_K_M.gguf Q5_K_M 1.840 GB large, very low quality loss - recommended
gemma-2b-openhermes-Q6_K.gguf Q6_K 2.062 GB very large, extremely low quality loss
gemma-2b-openhermes-Q8_0.gguf Q8_0 2.669 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-2b-openhermes-GGUF --include "gemma-2b-openhermes-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-2b-openhermes-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'