Hugging Face's logo

qwp4w3hyb
/
Hunyuan-A13B-Instruct-hf-WIP-GGUF

Text Generation
GGUF
conversational
Model card Files
xet
Community
1
qwp4w3hyb commited on
Commit
c9a7ab0
·
verified ·
1 Parent(s): f48eb32

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -9,6 +9,8 @@ pipeline_tag: text-generation
9
  ---
10
  # Alpha quality, needs WIP PR
11
 
 
 
12
  - Based on [ngxson/llama.cpp/pull/26](https://github.com/ngxson/llama.cpp/pull/26)@[46c8b70cbc7346db95e45ebae4f1e0c68a9b8d86](https://github.com/ngxson/llama.cpp/pull/26/commits/46c8b70cbc7346db95e45ebae4f1e0c68a9b8d86)
13
  - which is based on [ggml-org/llama.cpp/pull/14425](https://github.com/ggml-org/llama.cpp/pull/14425)
14
  - supposedly works *mostly fine*™ when run with below args according to [ggml-org/llama.cpp/pull/14425#issuecomment-3017533726](https://github.com/ggml-org/llama.cpp/pull/14425#issuecomment-3017533726)
 
9
  ---
10
  # Alpha quality, needs WIP PR
11
 
12
+
13
+ - The quants here are outdated, [bullerwins/Hunyuan-A13B-Instruct-GGUF](https://huggingface.co/bullerwins/Hunyuan-A13B-Instruct-GGUF) includes more recent fixes and will likely work better.
14
  - Based on [ngxson/llama.cpp/pull/26](https://github.com/ngxson/llama.cpp/pull/26)@[46c8b70cbc7346db95e45ebae4f1e0c68a9b8d86](https://github.com/ngxson/llama.cpp/pull/26/commits/46c8b70cbc7346db95e45ebae4f1e0c68a9b8d86)
15
  - which is based on [ggml-org/llama.cpp/pull/14425](https://github.com/ggml-org/llama.cpp/pull/14425)
16
  - supposedly works *mostly fine*™ when run with below args according to [ggml-org/llama.cpp/pull/14425#issuecomment-3017533726](https://github.com/ggml-org/llama.cpp/pull/14425#issuecomment-3017533726)