help-forum

577 threads · Page 1 of 12

How do I get Docker MCP Tools working in Text Gen??? 2 messages
Downloading folders from huggingface? 8 messages
Windows
Help 11 messages
Model generating incoherent replies after char reaches 4096 context size 15 messages
How does the file attachment mechanic work? 3 messages
Need help installing - tried everything, even ChatGPT for help 6 messages
Windows
What's up with max_new_tokens; Or what is stopping me from exceeding 4096 Tokens in Text-Gen Webu UI 15 messages
Setup Windows
Error when loading gguf through Llamma 22 messages
LLaMA Windows
Speaking out of turn 25 messages
Prompts & Characters
How tf do I keep facing the same error when I am loading model??? 2 messages
Any expert here can help me with the performance issue? 6 messages
Portable oobabooga doesn't apply/restart when checking extensions help 5 messages
Couldn't out of context be solved by deleting old messages? 7 messages
Prompts & Characters
Client doesn't show Listen Port when listening in selected and session is restarted 3 messages
Windows
Unable to interact with Web UI 8 messages
Linux Setup
Classifier Free Guidance via Intel SYCL? 4 messages
Linux
Dual GPU support for LLM inferencing? (Locally) 23 messages
Linux LLaMA Hardware Windows
Upgraded GPU from 3080 to 5080 - now model responses are borked 4 messages
im trying to load some models to do some light testing but i keep getting a warning message: 31 messages
modulenotfounderror: no module named "yaml" 3 messages
Did anyone manage to run a Qwen3 safetensor version on Windows? 7 messages
Setup Windows
Are there anyway to change from cpu only to NVIDIA acceleration? 19 messages
Windows
Error when running start.bat after updating. 7 messages
Windows
Weird model settings load error 5 messages
Error using ad_discordbot extention 3 messages
No module named 'llama_cpp_binaries' - windows 11 2 messages
LLaMA Windows
[solved] i have installation issue. help, please 4 messages
Windows
Won't detect models after running an update 6 messages
Windows
[SOLVED] Where llamacpp_HF? 4 messages
Linux Setup
Failed to load model 4 messages
Improving times and can't load AWQ model 4 messages
Windows
refuses to generate an output 3 messages
Windows
I keep getting an error when loading models 5 messages
Windows
character creation 28 messages
No web ui after install 34 messages
Linux Setup AMD
Does Ooba no longer download what's needed to run models? Issues loading both AWQ & GPTQ models 21 messages
Setup Windows
Help Model Fails to Generate Output on Linux 5 messages
Linux Setup AMD Prompts & Characters
Seeking for Gradio update methods 16 messages
Windows
can't run web-ui on a RTX5080 3 messages
Hardware Windows
failed to build the chat prompt. The input is too long for the available context length. 16 messages
Hardware Windows
Fail to load the model 110 messages
ERROR: Could not find a version that satisfies the requirement 2 messages
Fail with openAI API for embedding 9 messages
Upgrade RAM or VRAM: Slow text generation 14 messages
Windows
Privacy concerns with Gradio 13 messages
Gradio Windows
Looking for some knowledge about the languages which model uses. 2 messages
Prompts & Characters Windows
Tokenizer errors while trying to run merged Transformers model 5 messages
Gradio
Model not Loading-Qwen32B 42 messages
Setup Windows
My model is very slow because my chat log is very,very long. 20 messages
How to send context to Vram? 4 messages
Windows