dranger003
commited on
Commit
•
9dead2c
1
Parent(s):
9fc7c45
Update README.md
Browse files
README.md
CHANGED
@@ -9,4 +9,4 @@ The importance matrix was trained for ~50K tokens (105 batches of 512 tokens) us
|
|
9 |
**NOTE**: The new IQ3_M/IQ3_S/Q3_K_XS are currently causing a segfault during quantization, so I'll upload them once llama.cpp gets fixed.
|
10 |
| Layers | Context | [Template](https://huggingface.co/abacusai/Smaug-Mixtral-v0.1/blob/main/tokenizer_config.json#L32) |
|
11 |
| --- | --- | --- |
|
12 |
-
| <pre>32</pre> | <pre>32768</pre> | <pre
|
|
|
9 |
**NOTE**: The new IQ3_M/IQ3_S/Q3_K_XS are currently causing a segfault during quantization, so I'll upload them once llama.cpp gets fixed.
|
10 |
| Layers | Context | [Template](https://huggingface.co/abacusai/Smaug-Mixtral-v0.1/blob/main/tokenizer_config.json#L32) |
|
11 |
| --- | --- | --- |
|
12 |
+
| <pre>32</pre> | <pre>32768</pre> | <pre>\<s\>[INST] {prompt} [/INST]<br>{response}</pre> |
|