GGUF
English
sft
StableLM
Inference Endpoints
maddes8cht commited on
Commit
54830a3
·
1 Parent(s): 69f2f0e

"Update README.md"

Browse files
Files changed (1) hide show
  1. README.md +3 -2
README.md CHANGED
@@ -20,9 +20,10 @@ I'm constantly enhancing these model descriptions to provide you with the most r
20
  - Original model: [Nous-Capybara-3B-V1.9](https://huggingface.co/NousResearch/Nous-Capybara-3B-V1.9)
21
 
22
  # StableLM
23
- StableLM is a familiy of Models by Stability AI.
 
24
  ## Note:
25
- Current (as of. 2023-11-15) implementations of Llama.cpp only support GPU offloading up to 34 Layers.
26
  The model will crash immediately if -ngl is larger than 34.
27
  The model works fine however without any gpu acceleration.
28
 
 
20
  - Original model: [Nous-Capybara-3B-V1.9](https://huggingface.co/NousResearch/Nous-Capybara-3B-V1.9)
21
 
22
  # StableLM
23
+ This is a Model based on StableLM. Stablelm is a familiy of Language Models by Stability AI.
24
+
25
  ## Note:
26
+ Current (as of. 2023-11-15) implementations of Llama.cpp only support GPU offloading up to 34 Layers with these StableLM Models.
27
  The model will crash immediately if -ngl is larger than 34.
28
  The model works fine however without any gpu acceleration.
29