olmo-gguf / README.md
calcuis's picture
Update README.md
ee18348 verified
|
raw
history blame
951 Bytes
---
license: apache-2.0
language:
- en
base_model:
- allenai/OLMo-7B-0724-Instruct-hf
pipeline_tag: text-generation
---
## GGUF quantized version of OLMo-7B-0724-Instruct Model
project original [source](https://huggingface.co/allenai/OLMo-7B-0724-Instruct-hf)
Q_2_K (not nice)
Q_3_K_M (acceptable)
Q_4_K_M is recommanded (good for running with CPU as well)
Q_5_K_M (good in general)
Q_6_K is good also; if you want a better result; take this one instead of Q_5_K_M
Q_8_0 which is very good; need a reasonable size of RAM otherwise you might expect a long wait
f16 is similar to the original hf model; opt this or hf also fine; make sure you have a good machine
### how to run it
use any connector for interacting with gguf; i.e., [gguf-connector](https://pypi.org/project/gguf-connector/)
<img src="https://allenai.org/olmo/olmo-7b-animation.gif" alt="OLMo Logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>