-
-
**Steps to reproduce the problem:**
1. Create an agent with knowledge from `acorn.io`
2. Once all files are scarped , ingest all files.
Ingestion of 1 file fails
-
### Issue Summary
I've downloaded the pack today and have tried to start it but this mess…
-
### Describe the issue
I'm unsure how to save a model after it has been quantized using WOQ and then loading it using HF or PyTorch. Here is my code so far.
import torch
import intel_extension_f…
-
### System Info
Happens when doing `save_pretrained()` or `push_to_hub()` on a T5-small model with a single LoraConfig after doing `merge_and_unload()`.
This has now broken `merge_and_unload()` …
-
While our [draft charter](https://www.w3.org/2023/03/proposed-webmachinelearning-charter.html) says that the group:
> priority on building blocks required by well-known model architectures such as re…
-
INT4 Inference (CPU) example from README is not working on Windows 11.
```python
from transformers import AutoTokenizer
from intel_extension_for_transformers.transformers import AutoModelForCausa…
-
### Describe the bug
After webui update, gpu is not used anymore. I don't remember old version number or date, but it did say one_click.py was modified. webui was working on gpu before update, no c…
-
neuralchat already synced RESTful API with latest OpenAI protocol via 2e1c79d9b99db8bc004d67235fc6df51ca1d238e
But neuralchat frontend don't have field to assign system prompt.
**backend log**
``…
-
### Issue you'd like to raise.
I use Windows 11 Pro 64bit.
I installed Gpt4All with chosen model.
In the application settings it finds my GPU RTX 3060 12GB, I tried to set Auto or to set direct…