GGUF
TensorBlock
GGUF
Inference Endpoints
TensorBlock

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

HenryJJ/Instruct_Yi-6B_Dolly_CodeAlpaca - GGUF

This repo contains GGUF format model files for HenryJJ/Instruct_Yi-6B_Dolly_CodeAlpaca.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.

Prompt template


Model file specification

Filename Quant type File Size Description
Instruct_Yi-6B_Dolly_CodeAlpaca-Q2_K.gguf Q2_K 2.337 GB smallest, significant quality loss - not recommended for most purposes
Instruct_Yi-6B_Dolly_CodeAlpaca-Q3_K_S.gguf Q3_K_S 2.709 GB very small, high quality loss
Instruct_Yi-6B_Dolly_CodeAlpaca-Q3_K_M.gguf Q3_K_M 2.993 GB very small, high quality loss
Instruct_Yi-6B_Dolly_CodeAlpaca-Q3_K_L.gguf Q3_K_L 3.237 GB small, substantial quality loss
Instruct_Yi-6B_Dolly_CodeAlpaca-Q4_0.gguf Q4_0 3.479 GB legacy; small, very high quality loss - prefer using Q3_K_M
Instruct_Yi-6B_Dolly_CodeAlpaca-Q4_K_S.gguf Q4_K_S 3.503 GB small, greater quality loss
Instruct_Yi-6B_Dolly_CodeAlpaca-Q4_K_M.gguf Q4_K_M 3.674 GB medium, balanced quality - recommended
Instruct_Yi-6B_Dolly_CodeAlpaca-Q5_0.gguf Q5_0 4.204 GB legacy; medium, balanced quality - prefer using Q4_K_M
Instruct_Yi-6B_Dolly_CodeAlpaca-Q5_K_S.gguf Q5_K_S 4.204 GB large, low quality loss - recommended
Instruct_Yi-6B_Dolly_CodeAlpaca-Q5_K_M.gguf Q5_K_M 4.304 GB large, very low quality loss - recommended
Instruct_Yi-6B_Dolly_CodeAlpaca-Q6_K.gguf Q6_K 4.974 GB very large, extremely low quality loss
Instruct_Yi-6B_Dolly_CodeAlpaca-Q8_0.gguf Q8_0 6.442 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/Instruct_Yi-6B_Dolly_CodeAlpaca-GGUF --include "Instruct_Yi-6B_Dolly_CodeAlpaca-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/Instruct_Yi-6B_Dolly_CodeAlpaca-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
169
GGUF
Model size
6.06B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference API
Unable to determine this model's library. Check the docs .

Model tree for tensorblock/Instruct_Yi-6B_Dolly_CodeAlpaca-GGUF

Quantized
(1)
this model

Datasets used to train tensorblock/Instruct_Yi-6B_Dolly_CodeAlpaca-GGUF