Text Generation
GGUF
Dutch
trl
fietje
alignment-handbook
dpo
TensorBlock
GGUF
conversational
TensorBlock

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

BramVanroy/fietje-2-chat - GGUF

This repo contains GGUF format model files for BramVanroy/fietje-2-chat.

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
fietje-2-chat-Q2_K.gguf Q2_K 1.107 GB smallest, significant quality loss - not recommended for most purposes
fietje-2-chat-Q3_K_S.gguf Q3_K_S 1.248 GB very small, high quality loss
fietje-2-chat-Q3_K_M.gguf Q3_K_M 1.423 GB very small, high quality loss
fietje-2-chat-Q3_K_L.gguf Q3_K_L 1.572 GB small, substantial quality loss
fietje-2-chat-Q4_0.gguf Q4_0 1.599 GB legacy; small, very high quality loss - prefer using Q3_K_M
fietje-2-chat-Q4_K_S.gguf Q4_K_S 1.616 GB small, greater quality loss
fietje-2-chat-Q4_K_M.gguf Q4_K_M 1.734 GB medium, balanced quality - recommended
fietje-2-chat-Q5_0.gguf Q5_0 1.930 GB legacy; medium, balanced quality - prefer using Q4_K_M
fietje-2-chat-Q5_K_S.gguf Q5_K_S 1.930 GB large, low quality loss - recommended
fietje-2-chat-Q5_K_M.gguf Q5_K_M 2.000 GB large, very low quality loss - recommended
fietje-2-chat-Q6_K.gguf Q6_K 2.281 GB very large, extremely low quality loss
fietje-2-chat-Q8_0.gguf Q8_0 2.953 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/fietje-2-chat-GGUF --include "fietje-2-chat-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/fietje-2-chat-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
231
GGUF
Model size
2.78B params
Architecture
phi2

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Examples
Inference API (serverless) has been turned off for this model.

Model tree for tensorblock/fietje-2-chat-GGUF

Base model

microsoft/phi-2
Quantized
(3)
this model

Datasets used to train tensorblock/fietje-2-chat-GGUF