Update README.md
Browse files
README.md
CHANGED
|
@@ -18,6 +18,14 @@ This repo contains 4bit GPTQ models for GPU inference, quantised using [GPTQ-for
|
|
| 18 |
* [4bit GGML models for CPU inference](https://huggingface.co/TheBloke/wizardLM-7B-GGML)
|
| 19 |
* [Unquantised model in HF format](https://huggingface.co/TheBloke/wizardLM-7B-HF)
|
| 20 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
## GIBBERISH OUTPUT IN `text-generation-webui`?
|
| 22 |
|
| 23 |
Please read the Provided Files section below. You should use `wizardLM-7B-GPTQ-4bit-128g.no-act-order.safetensors` unless you are able to use the latest GPTQ-for-LLaMa code.
|
|
|
|
| 18 |
* [4bit GGML models for CPU inference](https://huggingface.co/TheBloke/wizardLM-7B-GGML)
|
| 19 |
* [Unquantised model in HF format](https://huggingface.co/TheBloke/wizardLM-7B-HF)
|
| 20 |
|
| 21 |
+
## PERFORMANCE ISSUES
|
| 22 |
+
|
| 23 |
+
I am currently working on re-creating these GPTQs due to performance issues reported by many people.
|
| 24 |
+
|
| 25 |
+
If you've not yet downloaded the models you might want to wait an hour to see if the new files I'm making now will fix this problem.
|
| 26 |
+
|
| 27 |
+
This message will disappear once the problem is resolved.
|
| 28 |
+
|
| 29 |
## GIBBERISH OUTPUT IN `text-generation-webui`?
|
| 30 |
|
| 31 |
Please read the Provided Files section below. You should use `wizardLM-7B-GPTQ-4bit-128g.no-act-order.safetensors` unless you are able to use the latest GPTQ-for-LLaMa code.
|