gpt4all
gpt4all copied to clipboard
nomic-ai
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
### Feature Request Allow users to specify a seed in the TypeScript API, like what this API does in the `LlamaContext` interface. Ideally this should be added to the `LLModelPromptContext`...
### Feature Request Are there any plans of supporting MoE models in the future? Models like the Granite3.1-3B and Mixtral-8x7B are popular MoE models. Their main appeal being high inference...
I haven't found any bug report that matched the issue I have found ### Bug Report In a directory with ".dart" files (text files with .dart extension) for a flutter...
If i load a modle and set all system promt and jinja and all and all if i rename the model-file -> all gone so model hash where be very...
from gpt4all import GPT4All # type: ignore model = GPT4All("DeepSeek-R1-Distill-Qwen-1.5B-Q4_0.gguf") output = model.generate("The capital of France is ", max_tokens=3) print(output) error output after model self-downloads: llama_model_load: error loading model: error...
### Documentation I can find where to change the proxy on the install screen, but where do I change the proxy after the app is installed?
### Bug Report When clicking "Updates" under the Settings menu, a window appears with the only option being to "Remove all components". Also, each successive click of the button launches...
The embedded copy of `kompute` fails to build with GCC 15 for two reasons. For one, there is an issue with the declaration of `vk`: ``` [ 33s] cd /home/abuild/rpmbuild/BUILD/python-gpt4all-3.4.2-build/gpt4all-3.4.2/gpt4all-backend/build/deps/llama.cpp-mainline/ggml/src/kompute/src...
I just tried to run the gpt4all-installer-linux.run file and got this error. qt.qpa.plugin: Could not find the Qt platform plugin "wayland" in "" This application failed to start because no...
### Feature Request When chatting with a model the page-up and page-down keys dont work. It would be nice if I could scroll using the keyboard.
