Jasper James
Jasper James
The following two models, quantised into gguf format using llamacpp, are created into ollama, and ollama's reasoning is severely hallucinated and never stops `https://huggingface.co/open-thoughts/OpenThinker-32B` `https://huggingface.co/huihui-ai/OpenThinker-32B-abliterated`
I'm using the gemma-3-27b-it model that VLLM is running on the backend, specifying openai_base_url as the api interface for VLLM in the marker. Marker command: ``` NUM_DEVICES=4 NUM_WORKERS=8 marker_single ug901-vivado-synthesis.pdf...
@VikParuchuri This line of code in the following file is incorrect, which prevents getting the output of ollama: `return json.loads(data)` -> `return data` ``` import base64 import json from io...
You have the following step in your X Narrate tutorial, why can't I find this in the ui? ``` 2. Install the extension: Open A1111 WebUl -> Click Tab "Extensions"...
### Question I am using the latest version of Docling to convert a PDF of about 300 pages that has more images, tables, code blocks.It takes a lot of time...
```python import time start_time = time.time() import dspy print(f"load dspy time: {time.time() - start_time} s") ``` ``` load dspy time: 5.986269474029541 s ```
## Summary * OS: Windows Server 2025 Datacenter * Architecture: 64-bit * Psutil version: 6.1.0 * Python version: Python 3.13.1 * Type: core ## Description I ran it on this...
If I use the cli command like this, the browser will quickly load the report: ``` vizviewer --once result.json ```  If I start the hosting server and then type...
Firstly, it is confirmed that this issue does not occur in Pyarmor version 9.2.0. Current situation: When packaging a PyQt6 application using Pyarmor, the application fails to launch properly and...