dranger003
commited on
Commit
•
e974a99
1
Parent(s):
a2d9080
Update README.md
Browse files
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
|
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.
|
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> |
|