Hugging Face's logo

dranger003
/
Qwen1.5-72B-Chat-iMat.GGUF

Text Generation
GGUF
Inference Endpoints
conversational
Model card Files Community
2
dranger003 commited on
Commit
ac3e9ed
•
1 Parent(s): 9e9c148

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -8,7 +8,7 @@ base_model: Qwen/Qwen1.5-72B-Chat
8
  ---
9
  <u>**NOTE**</u>: You will need a recent build of llama.cpp to run these quants (i.e. at least commit `494c870`).
10
 
11
- **2023-03-07**: Updating quants using latest build as things seem to have stabilized a bit now.
12
 
13
  GGUF importance matrix (imatrix) quants for https://huggingface.co/Qwen/Qwen1.5-72B-Chat
14
  * The importance matrix was trained for ~50K tokens (105 batches of 512 tokens) using a [general purpose imatrix calibration dataset](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384).
 
8
  ---
9
  <u>**NOTE**</u>: You will need a recent build of llama.cpp to run these quants (i.e. at least commit `494c870`).
10
 
11
+ **2023-03-07**: Refreshing quants using latest build as things seem to have stabilized a bit now.
12
 
13
  GGUF importance matrix (imatrix) quants for https://huggingface.co/Qwen/Qwen1.5-72B-Chat
14
  * The importance matrix was trained for ~50K tokens (105 batches of 512 tokens) using a [general purpose imatrix calibration dataset](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384).