Text Generation
Transformers
GGUF
English
Inference Endpoints
maddes8cht commited on
Commit
a0102fa
1 Parent(s): 42afb8e

"Update README.md"

Browse files
Files changed (1) hide show
  1. README.md +3 -4
README.md CHANGED
@@ -7,8 +7,6 @@ language:
7
  library_name: transformers
8
  pipeline_tag: text-generation
9
  ---
10
- # Dieses Modell ist kaputt!!
11
-
12
  [![banner](https://maddes8cht.github.io/assets/buttons/Huggingface-banner.jpg)]()
13
 
14
  I'm constantly enhancing these model descriptions to provide you with the most relevant and comprehensive information
@@ -18,10 +16,11 @@ I'm constantly enhancing these model descriptions to provide you with the most r
18
  - Original model: [Akins-3B](https://huggingface.co/acrastt/Akins-3B)
19
 
20
  # StableLM
21
- This is a Model based on StableLM. Stablelm is a familiy of Language Models by Stability AI.
 
22
 
23
  ## Note:
24
- Current (as of. 2023-11-15) implementations of Llama.cpp only support GPU offloading up to 34 Layers with these StableLM Models.
25
  The model will crash immediately if -ngl is larger than 34.
26
  The model works fine however without any gpu acceleration.
27
 
 
7
  library_name: transformers
8
  pipeline_tag: text-generation
9
  ---
 
 
10
  [![banner](https://maddes8cht.github.io/assets/buttons/Huggingface-banner.jpg)]()
11
 
12
  I'm constantly enhancing these model descriptions to provide you with the most relevant and comprehensive information
 
16
  - Original model: [Akins-3B](https://huggingface.co/acrastt/Akins-3B)
17
 
18
  # StableLM
19
+ This is a Model based on StableLM.
20
+ Stablelm is a familiy of Language Models by Stability AI.
21
 
22
  ## Note:
23
+ Current (as of 2023-11-15) implementations of Llama.cpp only support GPU offloading up to 34 Layers with these StableLM Models.
24
  The model will crash immediately if -ngl is larger than 34.
25
  The model works fine however without any gpu acceleration.
26