Hugging Face's logo

tensorblock
/
archangel_sft-dpo_pythia2-8b-GGUF

GGUF
English
human feedback
rlhf
preferences
alignment
HALO
halos
dpo
rl
TensorBlock
GGUF
Inference Endpoints
Model card Files Community
archangel_sft-dpo_pythia2-8b-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
64cc71b verified
preview code
|
raw
history blame contribute delete
5.32 kB
metadata
license: apache-2.0
datasets:
  - stanfordnlp/SHP
  - Anthropic/hh-rlhf
  - OpenAssistant/oasst1
language:
  - en
metrics:
  - accuracy
tags:
  - human feedback
  - rlhf
  - preferences
  - alignment
  - HALO
  - halos
  - dpo
  - rl
  - TensorBlock
  - GGUF
base_model: ContextualAI/archangel_sft-dpo_pythia2-8b
TensorBlock

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

ContextualAI/archangel_sft-dpo_pythia2-8b - GGUF

This repo contains GGUF format model files for ContextualAI/archangel_sft-dpo_pythia2-8b.

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

Prompt template

Model file specification

Filename Quant type File Size Description
archangel_sft-dpo_pythia2-8b-Q2_K.gguf Q2_K 1.086 GB smallest, significant quality loss - not recommended for most purposes
archangel_sft-dpo_pythia2-8b-Q3_K_S.gguf Q3_K_S 1.248 GB very small, high quality loss
archangel_sft-dpo_pythia2-8b-Q3_K_M.gguf Q3_K_M 1.478 GB very small, high quality loss
archangel_sft-dpo_pythia2-8b-Q3_K_L.gguf Q3_K_L 1.602 GB small, substantial quality loss
archangel_sft-dpo_pythia2-8b-Q4_0.gguf Q4_0 1.600 GB legacy; small, very high quality loss - prefer using Q3_K_M
archangel_sft-dpo_pythia2-8b-Q4_K_S.gguf Q4_K_S 1.613 GB small, greater quality loss
archangel_sft-dpo_pythia2-8b-Q4_K_M.gguf Q4_K_M 1.787 GB medium, balanced quality - recommended
archangel_sft-dpo_pythia2-8b-Q5_0.gguf Q5_0 1.930 GB legacy; medium, balanced quality - prefer using Q4_K_M
archangel_sft-dpo_pythia2-8b-Q5_K_S.gguf Q5_K_S 1.930 GB large, low quality loss - recommended
archangel_sft-dpo_pythia2-8b-Q5_K_M.gguf Q5_K_M 2.070 GB large, very low quality loss - recommended
archangel_sft-dpo_pythia2-8b-Q6_K.gguf Q6_K 2.282 GB very large, extremely low quality loss
archangel_sft-dpo_pythia2-8b-Q8_0.gguf Q8_0 2.954 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/archangel_sft-dpo_pythia2-8b-GGUF --include "archangel_sft-dpo_pythia2-8b-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/archangel_sft-dpo_pythia2-8b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'