Hugging Face's logo

tensorblock
/
SmolLM-360M-Instruct-GGUF

Transformers
GGUF
MLX
English
alignment-handbook
trl
sft
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
SmolLM-360M-Instruct-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
9a76e31 verified
preview code
|
raw
history blame
4.8 kB
metadata
license: apache-2.0
base_model: HuggingFaceTB/SmolLM-360M-Instruct
tags:
  - alignment-handbook
  - trl
  - sft
  - TensorBlock
  - GGUF
datasets:
  - Magpie-Align/Magpie-Pro-300K-Filtered
  - bigcode/self-oss-instruct-sc2-exec-filter-50k
  - teknium/OpenHermes-2.5
  - HuggingFaceTB/everyday-conversations-llama3.1-2k
library_name: transformers
language:
  - en
TensorBlock

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

HuggingFaceTB/SmolLM-360M-Instruct - GGUF

This repo contains GGUF format model files for HuggingFaceTB/SmolLM-360M-Instruct.

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

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
SmolLM-360M-Instruct-Q2_K.gguf Q2_K 0.204 GB smallest, significant quality loss - not recommended for most purposes
SmolLM-360M-Instruct-Q3_K_S.gguf Q3_K_S 0.204 GB very small, high quality loss
SmolLM-360M-Instruct-Q3_K_M.gguf Q3_K_M 0.219 GB very small, high quality loss
SmolLM-360M-Instruct-Q3_K_L.gguf Q3_K_L 0.229 GB small, substantial quality loss
SmolLM-360M-Instruct-Q4_0.gguf Q4_0 0.213 GB legacy; small, very high quality loss - prefer using Q3_K_M
SmolLM-360M-Instruct-Q4_K_S.gguf Q4_K_S 0.242 GB small, greater quality loss
SmolLM-360M-Instruct-Q4_K_M.gguf Q4_K_M 0.252 GB medium, balanced quality - recommended
SmolLM-360M-Instruct-Q5_0.gguf Q5_0 0.250 GB legacy; medium, balanced quality - prefer using Q4_K_M
SmolLM-360M-Instruct-Q5_K_S.gguf Q5_K_S 0.264 GB large, low quality loss - recommended
SmolLM-360M-Instruct-Q5_K_M.gguf Q5_K_M 0.270 GB large, very low quality loss - recommended
SmolLM-360M-Instruct-Q6_K.gguf Q6_K 0.342 GB very large, extremely low quality loss
SmolLM-360M-Instruct-Q8_0.gguf Q8_0 0.360 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/SmolLM-360M-Instruct-GGUF --include "SmolLM-360M-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/SmolLM-360M-Instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'