Hugging Face's logo

tensorblock
/
tulu-2-dpo-13b-GGUF

GGUF
English
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
tulu-2-dpo-13b-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
69a1d61 verified
preview code
|
raw
history blame contribute delete
4.78 kB
metadata
datasets:
  - HuggingFaceH4/ultrafeedback_binarized
  - allenai/tulu-v2-sft-mixture
language:
  - en
base_model: allenai/tulu-2-dpo-13b
license: other
license_name: ai2-impact-license-low-risk
license_link: https://allenai.org/impact-license
tags:
  - TensorBlock
  - GGUF
model-index:
  - name: tulu-2-dpo-13b
    results: []
TensorBlock

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

allenai/tulu-2-dpo-13b - GGUF

This repo contains GGUF format model files for allenai/tulu-2-dpo-13b.

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

Prompt template 

<|user|>
{prompt}
<|assistant|>

Model file specification

Filename Quant type File Size Description
tulu-2-dpo-13b-Q2_K.gguf Q2_K 4.521 GB smallest, significant quality loss - not recommended for most purposes
tulu-2-dpo-13b-Q3_K_S.gguf Q3_K_S 5.270 GB very small, high quality loss
tulu-2-dpo-13b-Q3_K_M.gguf Q3_K_M 5.903 GB very small, high quality loss
tulu-2-dpo-13b-Q3_K_L.gguf Q3_K_L 6.454 GB small, substantial quality loss
tulu-2-dpo-13b-Q4_0.gguf Q4_0 6.860 GB legacy; small, very high quality loss - prefer using Q3_K_M
tulu-2-dpo-13b-Q4_K_S.gguf Q4_K_S 6.913 GB small, greater quality loss
tulu-2-dpo-13b-Q4_K_M.gguf Q4_K_M 7.326 GB medium, balanced quality - recommended
tulu-2-dpo-13b-Q5_0.gguf Q5_0 8.356 GB legacy; medium, balanced quality - prefer using Q4_K_M
tulu-2-dpo-13b-Q5_K_S.gguf Q5_K_S 8.356 GB large, low quality loss - recommended
tulu-2-dpo-13b-Q5_K_M.gguf Q5_K_M 8.596 GB large, very low quality loss - recommended
tulu-2-dpo-13b-Q6_K.gguf Q6_K 9.946 GB very large, extremely low quality loss
tulu-2-dpo-13b-Q8_0.gguf Q8_0 12.881 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/tulu-2-dpo-13b-GGUF --include "tulu-2-dpo-13b-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/tulu-2-dpo-13b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'