zlacker
[return to "Mistral 7B Fine-Tune Optimized"]
◧
1. nickth+Cb
[view]
[source]
2023-12-20 20:55:18
>>tosh+(OP)
Anytime I see a claim that our 7b models are better than gpt-4 I basically stop reading. If you are going to make that claim, give me several easily digestible examples of this taking place.
◧◩
2. achill+Dc
[view]
[source]
2023-12-20 21:01:44
>>nickth+Cb
They can absolutely outperform gpt4 for specific use cases.
◧◩◪
3. nickth+1d
[view]
[source]
2023-12-20 21:03:55
>>achill+Dc
I am very open to believing that. I'd love to see some examples.
◧◩◪◨
4. shiftp+Uh
[view]
[source]
2023-12-20 21:31:37
>>nickth+1d
They're quite close in arena format:
https://chat.lmsys.org/?arena
◧◩◪◨⬒
5. TOMDM+2k
[view]
[source]
2023-12-20 21:45:53
>>shiftp+Uh
To be clear, Mixtral is very competitive, Mistral while certainly way better than most 7B models performs far worse than ChatGPT3.5 Turbo.
◧◩◪◨⬒⬓
6. shiftp+Bp
[view]
[source]
2023-12-20 22:18:30
>>TOMDM+2k
Apologies, that's what I get for skimming through the thread.
[go to top]