Hugging Face's logo

dranger003
/
Smaug-Mixtral-v0.1-iMat.GGUF

Text Generation
GGUF
Model card Files Community
1
dranger003 commited on
Commit
7e63145
•
1 Parent(s): 84c7cb4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -7,7 +7,7 @@ library_name: gguf
7
  * 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
  * The [imatrix is being used on the K-quants](https://github.com/ggerganov/llama.cpp/pull/4930) as well.
9
 
10
- **NOTE**: The new IQ3_M/IQ3_S (and updated Q3_K_XS) quants have been added, as well as IQ2_S/IQ2_M.
11
  | Layers | Context | [Template](https://huggingface.co/abacusai/Smaug-Mixtral-v0.1/blob/main/tokenizer_config.json#L32) |
12
  | --- | --- | --- |
13
  | <pre>32</pre> | <pre>32768</pre> | <pre>\<s\>[INST] {prompt} [/INST]<br>{response}</pre> |
 
7
  * 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
  * The [imatrix is being used on the K-quants](https://github.com/ggerganov/llama.cpp/pull/4930) as well.
9
 
10
+ **NOTE**: The new IQ3_M/IQ3_S (and updated Q3_K_XS) quants have been added, as well as IQ2_S/IQ2_M (requires commit a33e6a0d).
11
  | Layers | Context | [Template](https://huggingface.co/abacusai/Smaug-Mixtral-v0.1/blob/main/tokenizer_config.json#L32) |
12
  | --- | --- | --- |
13
  | <pre>32</pre> | <pre>32768</pre> | <pre>\<s\>[INST] {prompt} [/INST]<br>{response}</pre> |