Hugging Face's logo

tensorblock
/
II-Tulu-3B-SFT-GGUF

Transformers
GGUF
axolotl
Generated from Trainer
TensorBlock
GGUF
conversational
Model card Files Community
II-Tulu-3B-SFT-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
1e3aad5 verified
preview code
|
raw
history blame contribute delete
4.78 kB
metadata
library_name: transformers
license: other
base_model: phunguyen01/II-Tulu-3B-SFT
tags:
  - axolotl
  - generated_from_trainer
  - TensorBlock
  - GGUF
datasets:
  - allenai/tulu-3-sft-mixture
model-index:
  - name: II-Tulu-3B-SFT
    results: []
TensorBlock

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

phunguyen01/II-Tulu-3B-SFT - GGUF

This repo contains GGUF format model files for phunguyen01/II-Tulu-3B-SFT.

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

Prompt template 

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Model file specification

Filename Quant type File Size Description
II-Tulu-3B-SFT-Q2_K.gguf Q2_K 1.275 GB smallest, significant quality loss - not recommended for most purposes
II-Tulu-3B-SFT-Q3_K_S.gguf Q3_K_S 1.454 GB very small, high quality loss
II-Tulu-3B-SFT-Q3_K_M.gguf Q3_K_M 1.590 GB very small, high quality loss
II-Tulu-3B-SFT-Q3_K_L.gguf Q3_K_L 1.707 GB small, substantial quality loss
II-Tulu-3B-SFT-Q4_0.gguf Q4_0 1.823 GB legacy; small, very high quality loss - prefer using Q3_K_M
II-Tulu-3B-SFT-Q4_K_S.gguf Q4_K_S 1.834 GB small, greater quality loss
II-Tulu-3B-SFT-Q4_K_M.gguf Q4_K_M 1.930 GB medium, balanced quality - recommended
II-Tulu-3B-SFT-Q5_0.gguf Q5_0 2.170 GB legacy; medium, balanced quality - prefer using Q4_K_M
II-Tulu-3B-SFT-Q5_K_S.gguf Q5_K_S 2.170 GB large, low quality loss - recommended
II-Tulu-3B-SFT-Q5_K_M.gguf Q5_K_M 2.225 GB large, very low quality loss - recommended
II-Tulu-3B-SFT-Q6_K.gguf Q6_K 2.538 GB very large, extremely low quality loss
II-Tulu-3B-SFT-Q8_0.gguf Q8_0 3.285 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/II-Tulu-3B-SFT-GGUF --include "II-Tulu-3B-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/II-Tulu-3B-SFT-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'