Hugging Face's logo

tensorblock
/
leaderboard_inst_v1.3_Open-Hermes_LDCC-SOLAR-10.7B_SFT-GGUF

GGUF
trl
sft
Generated from Trainer
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
leaderboard_inst_v1.3_Open-Hermes_LDCC-SOLAR-10.7B_SFT-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
ac73be1 verified
preview code
|
raw
history blame contribute delete
6.49 kB
metadata
license: cc-by-nc-4.0
base_model: ENERGY-DRINK-LOVE/leaderboard_inst_v1.3_Open-Hermes_LDCC-SOLAR-10.7B_SFT
tags:
  - trl
  - sft
  - generated_from_trainer
  - TensorBlock
  - GGUF
datasets:
  - generator
model-index:
  - name: leaderboard_inst_v1.3_Open-Hermes_LDCC-SOLAR-10.7B_SFT
    results: []
TensorBlock

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

ENERGY-DRINK-LOVE/leaderboard_inst_v1.3_Open-Hermes_LDCC-SOLAR-10.7B_SFT - GGUF

This repo contains GGUF format model files for ENERGY-DRINK-LOVE/leaderboard_inst_v1.3_Open-Hermes_LDCC-SOLAR-10.7B_SFT.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

Prompt template 

### System:
{system_prompt}

### User:
{prompt}

### Assistant:

Model file specification

Filename Quant type File Size Description
leaderboard_inst_v1.3_Open-Hermes_LDCC-SOLAR-10.7B_SFT-Q2_K.gguf Q2_K 3.799 GB smallest, significant quality loss - not recommended for most purposes
leaderboard_inst_v1.3_Open-Hermes_LDCC-SOLAR-10.7B_SFT-Q3_K_S.gguf Q3_K_S 4.421 GB very small, high quality loss
leaderboard_inst_v1.3_Open-Hermes_LDCC-SOLAR-10.7B_SFT-Q3_K_M.gguf Q3_K_M 4.916 GB very small, high quality loss
leaderboard_inst_v1.3_Open-Hermes_LDCC-SOLAR-10.7B_SFT-Q3_K_L.gguf Q3_K_L 5.339 GB small, substantial quality loss
leaderboard_inst_v1.3_Open-Hermes_LDCC-SOLAR-10.7B_SFT-Q4_0.gguf Q4_0 5.740 GB legacy; small, very high quality loss - prefer using Q3_K_M
leaderboard_inst_v1.3_Open-Hermes_LDCC-SOLAR-10.7B_SFT-Q4_K_S.gguf Q4_K_S 5.783 GB small, greater quality loss
leaderboard_inst_v1.3_Open-Hermes_LDCC-SOLAR-10.7B_SFT-Q4_K_M.gguf Q4_K_M 6.103 GB medium, balanced quality - recommended
leaderboard_inst_v1.3_Open-Hermes_LDCC-SOLAR-10.7B_SFT-Q5_0.gguf Q5_0 6.982 GB legacy; medium, balanced quality - prefer using Q4_K_M
leaderboard_inst_v1.3_Open-Hermes_LDCC-SOLAR-10.7B_SFT-Q5_K_S.gguf Q5_K_S 6.982 GB large, low quality loss - recommended
leaderboard_inst_v1.3_Open-Hermes_LDCC-SOLAR-10.7B_SFT-Q5_K_M.gguf Q5_K_M 7.169 GB large, very low quality loss - recommended
leaderboard_inst_v1.3_Open-Hermes_LDCC-SOLAR-10.7B_SFT-Q6_K.gguf Q6_K 8.301 GB very large, extremely low quality loss
leaderboard_inst_v1.3_Open-Hermes_LDCC-SOLAR-10.7B_SFT-Q8_0.gguf Q8_0 10.751 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/leaderboard_inst_v1.3_Open-Hermes_LDCC-SOLAR-10.7B_SFT-GGUF --include "leaderboard_inst_v1.3_Open-Hermes_LDCC-SOLAR-10.7B_SFT-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/leaderboard_inst_v1.3_Open-Hermes_LDCC-SOLAR-10.7B_SFT-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'