Content
@
https://opensea.io/collection/dev-21
0 reply
0 recast
2 reactions
Nik The Savage🎩🥷
@nikthesavage
Chat gpt, Claude, Perplexity all are down for me It's time to use my mind abitðŸ«
4 replies
1 recast
3 reactions
eggman 🔵
@eggman.eth
Time to join the local llama group my friend Llama3-7b GGUF can be easily fit into a low end GPU, or run straight off your cpu and sram at acceptable speeds! Or if you need gpt4 level reasoning, cloud-hosted llama3 70b is your dude :)
1 reply
0 recast
0 reaction
Nik The Savage🎩🥷
@nikthesavage
Most agree TYSM for good suggestions Today, I feel the difference between open and closed models :)
1 reply
0 recast
1 reaction
eggman 🔵
@eggman.eth
oh man, there's so much out there on huggingface - llama3-70b-instruct is definitely the king right now imo, but if you need super large (and actually working) context windows, mixtral-8x7b is amazing. There's quantized versions of most big models there, and lots of fine-tunes for specific use-cases. Check them out!
1 reply
0 recast
0 reaction
Nik The Savage🎩🥷
@nikthesavage
I agree, what I see its much better for coding than gpt4 , gpt4 for is great but abit dumb for coding https://huggingface.co/stabilityai/stable-audio-open-1.0 Found this today and sounds cool to me maybe you like it too
1 reply
0 recast
1 reaction
eggman 🔵
@eggman.eth
oh damn, and brand new too! I'm a huge fan of stable diffusion and the civit/huggingface models, so will definitely try this out! And yeah, gpt4 is an odd one - especially gpt4o. It's as if it just got dumber as time went on when it came to code. Open model fine-tunes on hugging face though? *chef's kiss*
0 reply
0 recast
0 reaction
