grigio@alien.topB to LocalLLaMA@poweruser.forumEnglish · 1 year agoIs Open LLM Leaderboard reliable source ? yi:34B is at the top but I get better results with neural-chat:7B modelmessage-squaremessage-square23fedilinkarrow-up11arrow-down10file-text
arrow-up11arrow-down1message-squareIs Open LLM Leaderboard reliable source ? yi:34B is at the top but I get better results with neural-chat:7B modelgrigio@alien.topB to LocalLLaMA@poweruser.forumEnglish · 1 year agomessage-square23fedilinkfile-text
minus-squaremeetrais@alien.topBlinkfedilinkEnglisharrow-up1·1 year agoSame experience here. I got excellent results from quantized models of Intel-Neural-7B and Mistral-7B but bad results with quantized model of Yi-34B.
minus-squareInevitable_Host_1446@alien.topBlinkfedilinkEnglisharrow-up1·1 year agoI’m not sure what the point of Neural-7B is, given that it’s super censored corporate safety bot. If that’s what people want they might as well just use ChatGPT, which is faster and better otherwise.
minus-squareNixellion@alien.topBlinkfedilinkEnglisharrow-up1·1 year agoPrivacy and cost Also no, 7B is as fast or faster than ChatGPT depending on ChatGPT load.
minus-squaregrigio@alien.topOPBlinkfedilinkEnglisharrow-up1·11 months agoneural-chat from Intel is not censored! Just use a good system prompt
Same experience here. I got excellent results from quantized models of Intel-Neural-7B and Mistral-7B but bad results with quantized model of Yi-34B.
I’m not sure what the point of Neural-7B is, given that it’s super censored corporate safety bot. If that’s what people want they might as well just use ChatGPT, which is faster and better otherwise.
Privacy and cost Also no, 7B is as fast or faster than ChatGPT depending on ChatGPT load.
neural-chat from Intel is not censored! Just use a good system prompt