@balfrag to Technology • 1 year agoChatGPT In Trouble: OpenAI may go bankrupt by 2024, AI bot costs company $700,000 every daywww.firstpost.comexternal-linkmessage-square206arrow-up1597arrow-down1207file-textcross-posted to: [email protected]
arrow-up1390arrow-down1external-linkChatGPT In Trouble: OpenAI may go bankrupt by 2024, AI bot costs company $700,000 every daywww.firstpost.com@balfrag to Technology • 1 year agomessage-square206file-textcross-posted to: [email protected]
minus-square@[email protected]linkfedilinkEnglish10•1 year agoIts fine, i got my own LlaMa at home, it does almost the same as GPT
minus-square@RoyalEngineeringlinkEnglish10•1 year agoWhich one? What are your system specs? I’ve been thinking about doing this too.
minus-square@[email protected]linkfedilinkEnglish1•edit-21 year agouncensored vicuna 7b if i recall nvidia rtx 3060, 20 core intel cpu, 32gb ram
minus-square@average650linkEnglish1•1 year agoThe biggest issue I find is it’s just not as easy to use as chatgpt. I’m surprised no one has sold an easy to use consumer version.
minus-square@[email protected]linkfedilinkEnglish1•1 year agoAre you referring to https://gpt4all.io or something else? I was going to try this one but will welcome any recommendations.
minus-square@BetaDoggo_linkEnglish1•1 year agoIn terms of flexibility oobabooga’s text generation webui is the best as it supports nearly every model as ggml, gptq and transformers. For the model itself Nous-hermes-llama2 is one the best for easy use.
Its fine, i got my own LlaMa at home, it does almost the same as GPT
Which one? What are your system specs?
I’ve been thinking about doing this too.
uncensored vicuna 7b if i recall
nvidia rtx 3060, 20 core intel cpu, 32gb ram
The biggest issue I find is it’s just not as easy to use as chatgpt. I’m surprised no one has sold an easy to use consumer version.
Are you referring to https://gpt4all.io or something else? I was going to try this one but will welcome any recommendations.
In terms of flexibility oobabooga’s text generation webui is the best as it supports nearly every model as ggml, gptq and transformers.
For the model itself Nous-hermes-llama2 is one the best for easy use.
I’d like to know too!