Hi everyone,
I am attempting to build/connect to a model using the HF servers to do the heavy lifting, and my home computer to host a webpage to access the model from HF. I’m told I have to ask for access to the model, and I could really use some help here. I am open to using any one of these models:
tiiuae/falcon-7b-instruct
meta-llama/Llama-3.1-8B-Instruct
mistralai/Mistral-7B-Instruct-v0.2
NousResearch/Nous-Hermes-2-Mistral-7B
openai/gpt-oss-20b
qwen/qwen2-7b-instruct
CohereForAI/c4ai-command-r-plus
I am using CHAT GPTs help to build this new system. I bought a POWERSPEC G525 (it’s what I can afford) and I was able to get it to work LOCALLY but it’s much too slow in my opinion, and If I have the ability to have the HF servers do all the heavy lifting it would be great.
Can one of you point me in the right direction?