Commit
·
96379e3
1
Parent(s):
e432728
Update README.md
Browse files
README.md
CHANGED
|
@@ -38,7 +38,7 @@ tags:
|
|
| 38 |
|
| 39 |
# Please Stop Using WRONG unofficial quant models unless you know what you're doing
|
| 40 |
|
| 41 |
-
GPTQ quants
|
| 42 |
|
| 43 |
**Some problems with llama.cpp on GPT2Tokenizer, gotta fix soon...**
|
| 44 |
|
|
|
|
| 38 |
|
| 39 |
# Please Stop Using WRONG unofficial quant models unless you know what you're doing
|
| 40 |
|
| 41 |
+
GPTQ quants require a good dataset for calibration, and the default C4 dataset is not capable - [see the releated issue](https://huggingface.co/CausalLM/14B/discussions/3)
|
| 42 |
|
| 43 |
**Some problems with llama.cpp on GPT2Tokenizer, gotta fix soon...**
|
| 44 |
|