Hugging Face's logo

tensorblock
/
pythia-160m-dolphin-extended-GGUF

Transformers
GGUF
English
axolotl
relora
Generated from Trainer
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
pythia-160m-dolphin-extended-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
e8a63eb verified
preview code
|
raw
history blame contribute delete
5.41 kB
metadata
base_model: jtatman/pythia-160m-dolphin-extended
library_name: transformers
license: apache-2.0
tags:
  - axolotl
  - relora
  - generated_from_trainer
  - TensorBlock
  - GGUF
datasets:
  - cognitivecomputations/dolphin
  - llamafactory/alpaca_gpt4_en
language:
  - en
metrics:
  - accuracy
  - bleu
  - rouge
model-index:
  - name: pythia-160m-dolphin-extended
    results: []
TensorBlock

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

jtatman/pythia-160m-dolphin-extended - GGUF

This repo contains GGUF format model files for jtatman/pythia-160m-dolphin-extended.

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

Prompt template 

<|endoftext|>[INST] {prompt} [/INST]

Model file specification

Filename Quant type File Size Description
pythia-160m-dolphin-extended-Q2_K.gguf Q2_K 0.078 GB smallest, significant quality loss - not recommended for most purposes
pythia-160m-dolphin-extended-Q3_K_S.gguf Q3_K_S 0.087 GB very small, high quality loss
pythia-160m-dolphin-extended-Q3_K_M.gguf Q3_K_M 0.095 GB very small, high quality loss
pythia-160m-dolphin-extended-Q3_K_L.gguf Q3_K_L 0.099 GB small, substantial quality loss
pythia-160m-dolphin-extended-Q4_0.gguf Q4_0 0.103 GB legacy; small, very high quality loss - prefer using Q3_K_M
pythia-160m-dolphin-extended-Q4_K_S.gguf Q4_K_S 0.104 GB small, greater quality loss
pythia-160m-dolphin-extended-Q4_K_M.gguf Q4_K_M 0.110 GB medium, balanced quality - recommended
pythia-160m-dolphin-extended-Q5_0.gguf Q5_0 0.119 GB legacy; medium, balanced quality - prefer using Q4_K_M
pythia-160m-dolphin-extended-Q5_K_S.gguf Q5_K_S 0.119 GB large, low quality loss - recommended
pythia-160m-dolphin-extended-Q5_K_M.gguf Q5_K_M 0.124 GB large, very low quality loss - recommended
pythia-160m-dolphin-extended-Q6_K.gguf Q6_K 0.135 GB very large, extremely low quality loss
pythia-160m-dolphin-extended-Q8_0.gguf Q8_0 0.175 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/pythia-160m-dolphin-extended-GGUF --include "pythia-160m-dolphin-extended-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/pythia-160m-dolphin-extended-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'