TensorBlock

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

fierysurf/Ambari-7B-base-v0.1-sharded - GGUF

This repo contains GGUF format model files for fierysurf/Ambari-7B-base-v0.1-sharded.

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
Ambari-7B-base-v0.1-sharded-Q2_K.gguf Q2_K 2.616 GB smallest, significant quality loss - not recommended for most purposes
Ambari-7B-base-v0.1-sharded-Q3_K_S.gguf Q3_K_S 3.039 GB very small, high quality loss
Ambari-7B-base-v0.1-sharded-Q3_K_M.gguf Q3_K_M 3.389 GB very small, high quality loss
Ambari-7B-base-v0.1-sharded-Q3_K_L.gguf Q3_K_L 3.688 GB small, substantial quality loss
Ambari-7B-base-v0.1-sharded-Q4_0.gguf Q4_0 3.926 GB legacy; small, very high quality loss - prefer using Q3_K_M
Ambari-7B-base-v0.1-sharded-Q4_K_S.gguf Q4_K_S 3.957 GB small, greater quality loss
Ambari-7B-base-v0.1-sharded-Q4_K_M.gguf Q4_K_M 4.181 GB medium, balanced quality - recommended
Ambari-7B-base-v0.1-sharded-Q5_0.gguf Q5_0 4.761 GB legacy; medium, balanced quality - prefer using Q4_K_M
Ambari-7B-base-v0.1-sharded-Q5_K_S.gguf Q5_K_S 4.761 GB large, low quality loss - recommended
Ambari-7B-base-v0.1-sharded-Q5_K_M.gguf Q5_K_M 4.892 GB large, very low quality loss - recommended
Ambari-7B-base-v0.1-sharded-Q6_K.gguf Q6_K 5.648 GB very large, extremely low quality loss
Ambari-7B-base-v0.1-sharded-Q8_0.gguf Q8_0 7.315 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/Ambari-7B-base-v0.1-sharded-GGUF --include "Ambari-7B-base-v0.1-sharded-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/Ambari-7B-base-v0.1-sharded-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
129
GGUF
Model size
6.88B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

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

Model tree for tensorblock/Ambari-7B-base-v0.1-sharded-GGUF

Quantized
(1)
this model