LLMFarm
LLMFarm copied to clipboard
guinmoon
llama and other large language models on iOS and MacOS offline using GGML library.
App crashes when I run fine tune on Llama-3 model but works perfectly when I try on tinyllama: Thread 16: EXC_BAD_ACCESS (code=2, address=0x16b5a7c40) ...
My prompt format, following discussions I've seen here and on the llama.cpp repo is as follows: `"system{system_prompt}user{prompt}assistant\n"` For the `reverse_prompt`, I'm just using ``. The first response is coherent, but...
The title says it all. When I tried loading Stable Diffusion GGUF file into LLM farm and asking for prompt, it immediately crashes, even though my iPhone 15 Pro should...
Hello Artem. First, I want to thank you for the great app! Exactly what I'm searching for last week! It's cool we can import gguf models and you let us...
When trying to load Raven (RWKV 5), the application crashes and exits. There are no error messages displayed. Is it possible simply that the RWKV package needs updating?
How can the model get information from the internet or some other source, like pdf on the iPhone?
would be so cool to transcribe audio on an iDevice much better than with Siri.
   I tried qwen 0.5b, 1.8b, 4b, and 7b, and only 0.5b worked properly. However, the result was not as good as the official demo. The output included...
I'm trying to use this model: https://huggingface.co/SeaLLMs/SeaLLM-7B-v2.5-GGUF The SeaLLM-7B-v2.5 has the following preset for LM studio: https://huggingface.co/SeaLLMs/SeaLLM-7B-v2.5-GGUF/blob/main/seallm-v2.5.preset.json I don't know how to convert this into prompt format for LLMFarm. Please...
 I hope we can adjust --n-predict N to control the length of the generated text.
