Hugging Face's logo

TheBloke
/
manticore-13b-chat-pyg-GGML

Model card Files
xet
Community
1
TheBloke commited on
Commit
1b2f7dc
·
1 Parent(s): d17ea4b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -20,7 +20,7 @@ pipeline_tag: text-generation
20
 
21
  # Manticore 13B Chat GGML
22
 
23
- This is GGML format quantised 4-bit, 5-bit and 8-bit models of [OpenAccess AI Collective's Manticore 13B Chat](https://huggingface.co/openaccess-ai-collective/manticore-13b-chat-pyg/edit/main/README.md).
24
 
25
  This repo is the result of quantising to 4-bit, 5-bit and 8-bit GGML for CPU (+CUDA) inference using [llama.cpp](https://github.com/ggerganov/llama.cpp).
26
 
 
20
 
21
  # Manticore 13B Chat GGML
22
 
23
+ This is GGML format quantised 4-bit, 5-bit and 8-bit models of [OpenAccess AI Collective's Manticore 13B Chat](https://huggingface.co/openaccess-ai-collective/manticore-13b-chat-pyg).
24
 
25
  This repo is the result of quantising to 4-bit, 5-bit and 8-bit GGML for CPU (+CUDA) inference using [llama.cpp](https://github.com/ggerganov/llama.cpp).
26