-
I think it'd be a good idea to support it as I'd like to be able to use [Text-gen-webui](https://github.com/oobabooga/text-generation-webui) instead of [KoboldAI](https://github.com/henk717/KoboldAI) …
-
./play-rocm.sh
Colab Check: False, TPU: False
Traceback (most recent call last):
File "aiserver.py", line 604, in
from modeling.inference_models.hf_torch_4bit import load_model_gptq_settin…
-
Hi,
I had great success with this project when using ollama.
I swapped to a model that runs on koboldai (openai compatible) and now the bot responses take ages.
It processes the input quick…
-
### System Info
- `transformers` version: 4.28.0.dev0
- Platform: Windows-10-10.0.22621-SP0
- Python version: 3.10.10
- Huggingface_hub version: 0.13.4
- Safetensors version: not installed
- PyT…
qtrrb updated
1 month ago
-
### 🐛 Describe the bug
When trying to run Stable Diffusion using ComfyUI, I get the following error since upgrading my CPU from a Ryzen 5600X to a Ryzen 7800X3D. Before the upgrade, it worked without…
-
I want to ban tokens, such as "###instruction" or "" (as they often are being generated by the model and it annoys me) but specifying them always results in a json error when executing the file.
He…
-
### System Info
Hi @harrisoUnable to load the model logged using mlflow
```
import mlflow
logged_model = 'runs:/runid/sql_database_chain'
# Load model as a PyFuncModel.
loaded_model = mlflow.pyf…
-
Not sure what I'm missing here, saw a similar issue brought up with the ERROR 193 but the code looks different.
C:\Users\ZURG\OneDrive\Desktop\Bold\KoboldAI-Client-main>play --remote
Runtime lau…
-
In models based on the mistral nemo enabling 'DRY Repetition Penalty' causes about 20 seconds of additional initialization time each time, on Radeon 6900xt.
In the Rocm version using rocm there i…
-
Version 1.71 used to work perfectly with Llama 3.1 8b with 32k of context and 10 GPU layers for me, but now, right after updating, it doesn't work with even 1 layer. I tested it on version 1.71, runni…