alain40
alain40
Experiencing the exact same error under Ubuntu
No I gave up. AR On Sun, Feb 11, 2018 at 7:26 AM, suke27 wrote: > i also face this problem, do you resolve it > > — > You...
Is this to say that a way to leverage CFG for assistant tuned models would be a relative text weight syntax à la Midjourney? /imagine football game::1 old coach::3 This...
More on this: latest build, snapdragon 8 Gen 2, termux - Qn_K models are garbled with -ngl > 0, but work fine with -ngl = 0 - Qn_0 legacy format...
Which LoRA? I use text-web-ui because of its convenience (I think this is common, warning small sample size). text-web-ui uses the peft huggingface library. That library provides the following default...
LoRA use case My use cases involve training on personal or work text documents. With training LLM gives more coherent answers that just by searching a vector db for embedding...
No question about it, there are use cases where changing LLM "mode" by dynamically loading LoRAs would be very valuable.
Confirming that open_llama_13b, quantized with GPTQ for Llama to 4 bits/32g, works well .