PacmanIncarnate commited on
Commit
53186f8
1 Parent(s): 052094a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -14,9 +14,9 @@ Conveniently download this model from the Faraday.dev app model manager.
14
  ***
15
 
16
  # What is a GGUF?
17
- GGUF is a format of large language model (LLM) that can be split between both CPU and GPU. GGUFs are compatible with apps based on llama.cpp, such as Faraday.dev. Where other formats require higher end GPUs, GGUFs can be run on a wider variety of hardware efficiently.
18
 
19
- GGUF models are quantized to reduce resource usage, with a tradeoff of reduced coherence at lower quantization. Quantization reduces the precision of the model weights by changing the number of bits used for each weight.
20
 
21
  ***
22
 
@@ -28,4 +28,4 @@ GGUF models are quantized to reduce resource usage, with a tradeoff of reduced c
28
  - High quality character hub.
29
  - Zero-config desktop-to-mobile tethering.
30
 
31
- Faraday makes it easy to start chatting with AI using your own characters or one of thr many found in thr built-in character hub. The model manager helps youbfind thr latest and greatest models and manager your collection of local models. A focus on ease of use doesn't mean Faraday lacks features or control. Faraday supports advanced features such as lorebooks, author's note, text formatting, custom context size, sampler settings, grammars, local TTS, cloud inference, and tethering, all implemented in a way that is straightforward and reliable.
 
14
  ***
15
 
16
  # What is a GGUF?
17
+ GGUF is a large language model (LLM) format that can be split between CPU and GPU. GGUFs are compatible with applications based on llama.cpp, such as Faraday.dev. Where other model formats require higher end GPUs with ample VRAM, GGUFs can be efficiently run on a wider variety of hardware.
18
 
19
+ GGUF models are quantized to reduce resource usage, with a tradeoff of reduced coherence at lower quantizations. Quantization reduces the precision of the model weights by changing the number of bits used for each weight.
20
 
21
  ***
22
 
 
28
  - High quality character hub.
29
  - Zero-config desktop-to-mobile tethering.
30
 
31
+ Faraday makes it easy to start chatting with AI using your own characters or one of the many found in the built-in character hub. The model manager helps you find the latest and greatest models. A focus on ease of use doesn't mean Faraday lacks features or removes control. Faraday supports advanced features such as lorebooks, author's note, text formatting, custom context size, sampler settings, grammars, local TTS, cloud inference, and tethering, all implemented in a way that is straightforward and reliable.