Hugging Face's logo

tensorblock
/
AceMath-1.5B-Instruct-GGUF

Text Generation
GGUF
PyTorch
English
nvidia
AceMath
math
CoT
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
AceMath-1.5B-Instruct-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
26e365d verified
preview code
|
raw
history blame contribute delete
5.09 kB
metadata
license: cc-by-nc-4.0
language:
  - en
pipeline_tag: text-generation
tags:
  - nvidia
  - AceMath
  - math
  - CoT
  - pytorch
  - TensorBlock
  - GGUF
base_model: nvidia/AceMath-1.5B-Instruct
TensorBlock

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

nvidia/AceMath-1.5B-Instruct - GGUF

This repo contains GGUF format model files for nvidia/AceMath-1.5B-Instruct.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4823.

Prompt template 

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}
Please give a step-by-step answer and use a oxed command to denote the final answer.<|im_end|>
<|im_start|>assistant

Model file specification

Filename Quant type File Size Description
AceMath-1.5B-Instruct-Q2_K.gguf Q2_K 0.753 GB smallest, significant quality loss - not recommended for most purposes
AceMath-1.5B-Instruct-Q3_K_S.gguf Q3_K_S 0.861 GB very small, high quality loss
AceMath-1.5B-Instruct-Q3_K_M.gguf Q3_K_M 0.924 GB very small, high quality loss
AceMath-1.5B-Instruct-Q3_K_L.gguf Q3_K_L 0.980 GB small, substantial quality loss
AceMath-1.5B-Instruct-Q4_0.gguf Q4_0 1.066 GB legacy; small, very high quality loss - prefer using Q3_K_M
AceMath-1.5B-Instruct-Q4_K_S.gguf Q4_K_S 1.072 GB small, greater quality loss
AceMath-1.5B-Instruct-Q4_K_M.gguf Q4_K_M 1.117 GB medium, balanced quality - recommended
AceMath-1.5B-Instruct-Q5_0.gguf Q5_0 1.259 GB legacy; medium, balanced quality - prefer using Q4_K_M
AceMath-1.5B-Instruct-Q5_K_S.gguf Q5_K_S 1.259 GB large, low quality loss - recommended
AceMath-1.5B-Instruct-Q5_K_M.gguf Q5_K_M 1.285 GB large, very low quality loss - recommended
AceMath-1.5B-Instruct-Q6_K.gguf Q6_K 1.464 GB very large, extremely low quality loss
AceMath-1.5B-Instruct-Q8_0.gguf Q8_0 1.895 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/AceMath-1.5B-Instruct-GGUF --include "AceMath-1.5B-Instruct-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/AceMath-1.5B-Instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'