tensorblock/plamo-13b-instruct-GGUF

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

pfnet/plamo-13b-instruct - GGUF

This repo contains GGUF format model files for pfnet/plamo-13b-instruct.

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

Run them on the TensorBlock client using your local machine ↗

Prompt template

以下はタスクを説明する指示で、文脈を説明した入力とペアになっています。要求を適切に補完するよう応答を書いてください。

### 指示:
{system_prompt}

### 入力:
{prompt}

### 応答:

Model file specification

Filename	Quant type	File Size	Description
plamo-13b-instruct-Q2_K.gguf	Q2_K	4.911 GB	smallest, significant quality loss - not recommended for most purposes
plamo-13b-instruct-Q3_K_S.gguf	Q3_K_S	5.732 GB	very small, high quality loss
plamo-13b-instruct-Q3_K_M.gguf	Q3_K_M	6.363 GB	very small, high quality loss
plamo-13b-instruct-Q3_K_L.gguf	Q3_K_L	6.914 GB	small, substantial quality loss
plamo-13b-instruct-Q4_0.gguf	Q4_0	7.437 GB	legacy; small, very high quality loss - prefer using Q3_K_M
plamo-13b-instruct-Q4_K_S.gguf	Q4_K_S	7.492 GB	small, greater quality loss
plamo-13b-instruct-Q4_K_M.gguf	Q4_K_M	7.893 GB	medium, balanced quality - recommended
plamo-13b-instruct-Q5_0.gguf	Q5_0	9.042 GB	legacy; medium, balanced quality - prefer using Q4_K_M
plamo-13b-instruct-Q5_K_S.gguf	Q5_K_S	9.042 GB	large, low quality loss - recommended
plamo-13b-instruct-Q5_K_M.gguf	Q5_K_M	9.277 GB	large, very low quality loss - recommended
plamo-13b-instruct-Q6_K.gguf	Q6_K	10.748 GB	very large, extremely low quality loss
plamo-13b-instruct-Q8_0.gguf	Q8_0	13.920 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/plamo-13b-instruct-GGUF --include "plamo-13b-instruct-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/plamo-13b-instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'