Hugging Face's logo

tensorblock
/
SmolLM2-360M-Instruct-FT-GGUF

Text Generation
Transformers
GGUF
Russian
rag
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
SmolLM2-360M-Instruct-FT-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
1b20d06 verified
preview code
|
raw
history blame
5.17 kB
metadata
library_name: transformers
license: apache-2.0
datasets:
  - Vikhrmodels/GrandMaster-PRO-MAX
language:
  - ru
base_model: belyakoff/SmolLM2-360M-Instruct-FT
pipeline_tag: text-generation
tags:
  - rag
  - TensorBlock
  - GGUF
TensorBlock

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

belyakoff/SmolLM2-360M-Instruct-FT - GGUF

This repo contains GGUF format model files for belyakoff/SmolLM2-360M-Instruct-FT.

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
SmolLM2-360M-Instruct-FT-Q2_K.gguf Q2_K 0.219 GB smallest, significant quality loss - not recommended for most purposes
SmolLM2-360M-Instruct-FT-Q3_K_S.gguf Q3_K_S 0.219 GB very small, high quality loss
SmolLM2-360M-Instruct-FT-Q3_K_M.gguf Q3_K_M 0.235 GB very small, high quality loss
SmolLM2-360M-Instruct-FT-Q3_K_L.gguf Q3_K_L 0.246 GB small, substantial quality loss
SmolLM2-360M-Instruct-FT-Q4_0.gguf Q4_0 0.229 GB legacy; small, very high quality loss - prefer using Q3_K_M
SmolLM2-360M-Instruct-FT-Q4_K_S.gguf Q4_K_S 0.260 GB small, greater quality loss
SmolLM2-360M-Instruct-FT-Q4_K_M.gguf Q4_K_M 0.271 GB medium, balanced quality - recommended
SmolLM2-360M-Instruct-FT-Q5_0.gguf Q5_0 0.268 GB legacy; medium, balanced quality - prefer using Q4_K_M
SmolLM2-360M-Instruct-FT-Q5_K_S.gguf Q5_K_S 0.283 GB large, low quality loss - recommended
SmolLM2-360M-Instruct-FT-Q5_K_M.gguf Q5_K_M 0.290 GB large, very low quality loss - recommended
SmolLM2-360M-Instruct-FT-Q6_K.gguf Q6_K 0.367 GB very large, extremely low quality loss
SmolLM2-360M-Instruct-FT-Q8_0.gguf Q8_0 0.386 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/SmolLM2-360M-Instruct-FT-GGUF --include "SmolLM2-360M-Instruct-FT-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/SmolLM2-360M-Instruct-FT-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'