34 lines
739 B
Markdown
34 lines
739 B
Markdown
|
---
|
||
|
|
license: other
|
||
|
|
license_name: lfm1.0
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
- ar
|
||
|
|
- zh
|
||
|
|
- fr
|
||
|
|
- de
|
||
|
|
- ja
|
||
|
|
- ko
|
||
|
|
- es
|
||
|
|
- pt
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
tags:
|
||
|
|
- liquid
|
||
|
|
- lfm2.5
|
||
|
|
- edge
|
||
|
|
- gguf
|
||
|
|
- llama
|
||
|
|
- text-generation
|
||
|
|
base_model:
|
||
|
|
- LiquidAI/LFM2.5-8B-A1B
|
||
|
|
---
|
||
|
|
|
||
|
|
# LFM2.5-8B-A1B-i1-GGUF
|
||
|
|
|
||
|
|
This repository contains GGUF format quantizations of the model LiquidAI/LFM2.5-8B-A1B. These models were generated using llama.cpp with an importance matrix (imatrix) - https://gist.github.com/bartowski1182/82ae9b520227f57d79ba04add13d0d0d
|
||
|
|
|
||
|
|
Used this pull request to be able to quantize: https://github.com/ggml-org/llama.cpp/pull/23826/
|
||
|
|
Should work with the latest llama.cpp
|
||
|
|
|
||
|
|
# NOTE
|
||
|
|
Quantization below 4 bits may result in unacceptably low quality.
|