Hugging Face's logo

onicai
/
llama_cpp_canister_models

GGUF
English
Model card Files
xet
 Community
icpp commited on
Commit
edd1ee4
·
verified ·
1 Parent(s): cb8528a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -2
README.md CHANGED
@@ -6,10 +6,12 @@ language:
6
 
7
  # On-chain llama.cpp - Internet Computer
8
 
 
9
 
10
- - Run on-chain (Internet Computer) with [onicai/llama_cpp_canister](https://github.com/onicai/llama_cpp_canister)
11
- - Run local with [ggerganov/llama.cpp](https://github.com/ggerganov/llama.cpp)
12
  - Try them out at [ICGPT](https://icgpt.icpp.world/)
 
 
13
  - The models were created with the training procedure outlined in [karpathy/llama2.c](https://github.com/karpathy/llama2.c) and then converted into *.gguf format as described below.
14
 
15
 
 
6
 
7
  # On-chain llama.cpp - Internet Computer
8
 
9
+ You can run any *.gguf file in a llama_cpp_canister, but these are smaller models you can use for testing [onicai/llama_cpp_canister](https://github.com/onicai/llama_cpp_canister)
10
 
11
+ Notes:
 
12
  - Try them out at [ICGPT](https://icgpt.icpp.world/)
13
+ - To use on the Internet Computer, follow instructions of [onicai/llama_cpp_canister](https://github.com/onicai/llama_cpp_canister)
14
+ - Run local with [ggerganov/llama.cpp](https://github.com/ggerganov/llama.cpp)
15
  - The models were created with the training procedure outlined in [karpathy/llama2.c](https://github.com/karpathy/llama2.c) and then converted into *.gguf format as described below.
16
 
17