Hugging Face's logo

tensorblock
/
Bitnet-SmolLM-135M-GGUF

Transformers
GGUF
English
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
Bitnet-SmolLM-135M-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
ff0ef3d verified
preview code
|
raw
history blame contribute delete
4.89 kB
metadata
library_name: transformers
license: apache-2.0
language:
  - en
datasets:
  - abideen/Cosmopedia-100k-pretrain
tags:
  - TensorBlock
  - GGUF
base_model: ighoshsubho/Bitnet-SmolLM-135M
TensorBlock

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

ighoshsubho/Bitnet-SmolLM-135M - GGUF

This repo contains GGUF format model files for ighoshsubho/Bitnet-SmolLM-135M.

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
Bitnet-SmolLM-135M-Q2_K.gguf Q2_K 0.043 GB smallest, significant quality loss - not recommended for most purposes
Bitnet-SmolLM-135M-Q3_K_S.gguf Q3_K_S 0.045 GB very small, high quality loss
Bitnet-SmolLM-135M-Q3_K_M.gguf Q3_K_M 0.047 GB very small, high quality loss
Bitnet-SmolLM-135M-Q3_K_L.gguf Q3_K_L 0.048 GB small, substantial quality loss
Bitnet-SmolLM-135M-Q4_0.gguf Q4_0 0.049 GB legacy; small, very high quality loss - prefer using Q3_K_M
Bitnet-SmolLM-135M-Q4_K_S.gguf Q4_K_S 0.049 GB small, greater quality loss
Bitnet-SmolLM-135M-Q4_K_M.gguf Q4_K_M 0.049 GB medium, balanced quality - recommended
Bitnet-SmolLM-135M-Q5_0.gguf Q5_0 0.052 GB legacy; medium, balanced quality - prefer using Q4_K_M
Bitnet-SmolLM-135M-Q5_K_S.gguf Q5_K_S 0.052 GB large, low quality loss - recommended
Bitnet-SmolLM-135M-Q5_K_M.gguf Q5_K_M 0.053 GB large, very low quality loss - recommended
Bitnet-SmolLM-135M-Q6_K.gguf Q6_K 0.056 GB very large, extremely low quality loss
Bitnet-SmolLM-135M-Q8_0.gguf Q8_0 0.072 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/Bitnet-SmolLM-135M-GGUF --include "Bitnet-SmolLM-135M-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/Bitnet-SmolLM-135M-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'