Commit
·
e432728
1
Parent(s):
1304cb3
Update README.md
Browse files
README.md
CHANGED
|
@@ -36,6 +36,12 @@ tags:
|
|
| 36 |
|
| 37 |
**Some problems with llama.cpp on GPT2Tokenizer, gotta fix soon...**
|
| 38 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
## Read Me:
|
| 40 |
|
| 41 |
Also see [14B Version](https://huggingface.co/CausalLM/14B)
|
|
|
|
| 36 |
|
| 37 |
**Some problems with llama.cpp on GPT2Tokenizer, gotta fix soon...**
|
| 38 |
|
| 39 |
+
# Please Stop Using WRONG unofficial quant models unless you know what you're doing
|
| 40 |
+
|
| 41 |
+
GPTQ quants requires 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 |
+
|
| 45 |
## Read Me:
|
| 46 |
|
| 47 |
Also see [14B Version](https://huggingface.co/CausalLM/14B)
|