dranger003
/

openbuddy-qwen1.5-14b-v20.1-32k-iMat.GGUF

Model card Files Files and versions Community

dranger003 commited on Mar 24

Commit

842bd26

•

1 Parent(s): 4506960

Update README.md

Files changed (1) hide show

README.md +6 -0

README.md CHANGED Viewed

@@ -4,3 +4,9 @@ license_name: tongyi-qianwen-license-agreement
 license_link: >-
   https://huggingface.co/Qwen/Qwen1.5-14B/blob/39b74a78357df4d2296e838d87565967d663a67a/LICENSE
 ---

 license_link: >-
   https://huggingface.co/Qwen/Qwen1.5-14B/blob/39b74a78357df4d2296e838d87565967d663a67a/LICENSE
 ---
+GGUF importance matrix (imatrix) quants for https://huggingface.co/OpenBuddy/openbuddy-qwen1.5-14b-v20.1-32k
+The importance matrix was trained for 100K tokens (200 batches of 512 tokens) using wiki.train.raw.
+| Layers | Context | [Template](https://huggingface.co/OpenBuddy/openbuddy-qwen1.5-14b-v20.1-32k/blob/main/tokenizer_config.json#L31) |
+| --- | --- | --- |
+| <pre>40</pre> | <pre>32768</pre> | <pre>\<\|im_start\|\>user<br>{prompt}\<\|im_end\|\><br>\<\|im_start\|\>assistant<br>{response}</pre> |