Hugging Face's logo

tensorblock
/
gpt3_125M_edu_hermes-GGUF

Text Generation
Transformers
GGUF
English
llm.c
TensorBlock
GGUF
Inference Endpoints
Model card Files Community
gpt3_125M_edu_hermes-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
470cc65 verified
preview code
|
raw
history blame contribute delete
4.9 kB
metadata
library_name: transformers
tags:
  - llm.c
  - TensorBlock
  - GGUF
license: mit
datasets:
  - HuggingFaceFW/fineweb-edu
  - teknium/OpenHermes-2.5
language:
  - en
pipeline_tag: text-generation
base_model: jrahn/gpt3_125M_edu_hermes
TensorBlock

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

jrahn/gpt3_125M_edu_hermes - GGUF

This repo contains GGUF format model files for jrahn/gpt3_125M_edu_hermes.

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
gpt3_125M_edu_hermes-Q2_K.gguf Q2_K 0.084 GB smallest, significant quality loss - not recommended for most purposes
gpt3_125M_edu_hermes-Q3_K_S.gguf Q3_K_S 0.093 GB very small, high quality loss
gpt3_125M_edu_hermes-Q3_K_M.gguf Q3_K_M 0.101 GB very small, high quality loss
gpt3_125M_edu_hermes-Q3_K_L.gguf Q3_K_L 0.105 GB small, substantial quality loss
gpt3_125M_edu_hermes-Q4_0.gguf Q4_0 0.110 GB legacy; small, very high quality loss - prefer using Q3_K_M
gpt3_125M_edu_hermes-Q4_K_S.gguf Q4_K_S 0.110 GB small, greater quality loss
gpt3_125M_edu_hermes-Q4_K_M.gguf Q4_K_M 0.116 GB medium, balanced quality - recommended
gpt3_125M_edu_hermes-Q5_0.gguf Q5_0 0.125 GB legacy; medium, balanced quality - prefer using Q4_K_M
gpt3_125M_edu_hermes-Q5_K_S.gguf Q5_K_S 0.125 GB large, low quality loss - recommended
gpt3_125M_edu_hermes-Q5_K_M.gguf Q5_K_M 0.130 GB large, very low quality loss - recommended
gpt3_125M_edu_hermes-Q6_K.gguf Q6_K 0.142 GB very large, extremely low quality loss
gpt3_125M_edu_hermes-Q8_0.gguf Q8_0 0.181 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/gpt3_125M_edu_hermes-GGUF --include "gpt3_125M_edu_hermes-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/gpt3_125M_edu_hermes-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'