metadata
license: apache-2.0
datasets:
- HuggingFaceTB/cosmopedia
language:
- en
inference:
parameters:
temperature: 0.6
top_p: 0.95
top_k: 50
repetition_penalty: 1.2
widget:
- text: Photosynthesis is
example_title: Textbook
group: Completion
- text: '<s> [INST] How to take care of plants? [/INST] '
example_title: Wikihow
group: Completion
- text: '<s> [INST] Generate a story about a flying cat [/INST] '
example_title: Story
group: Completion
base_model: HuggingFaceTB/cosmo-1b
tags:
- TensorBlock
- GGUF
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
HuggingFaceTB/cosmo-1b - GGUF
This repo contains GGUF format model files for HuggingFaceTB/cosmo-1b.
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 |
|---|---|---|---|
| cosmo-1b-Q2_K.gguf | Q2_K | 0.666 GB | smallest, significant quality loss - not recommended for most purposes |
| cosmo-1b-Q3_K_S.gguf | Q3_K_S | 0.775 GB | very small, high quality loss |
| cosmo-1b-Q3_K_M.gguf | Q3_K_M | 0.858 GB | very small, high quality loss |
| cosmo-1b-Q3_K_L.gguf | Q3_K_L | 0.931 GB | small, substantial quality loss |
| cosmo-1b-Q4_0.gguf | Q4_0 | 0.998 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| cosmo-1b-Q4_K_S.gguf | Q4_K_S | 1.006 GB | small, greater quality loss |
| cosmo-1b-Q4_K_M.gguf | Q4_K_M | 1.063 GB | medium, balanced quality - recommended |
| cosmo-1b-Q5_0.gguf | Q5_0 | 1.207 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| cosmo-1b-Q5_K_S.gguf | Q5_K_S | 1.207 GB | large, low quality loss - recommended |
| cosmo-1b-Q5_K_M.gguf | Q5_K_M | 1.241 GB | large, very low quality loss - recommended |
| cosmo-1b-Q6_K.gguf | Q6_K | 1.430 GB | very large, extremely low quality loss |
| cosmo-1b-Q8_0.gguf | Q8_0 | 1.852 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/cosmo-1b-GGUF --include "cosmo-1b-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/cosmo-1b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'