has anyone had success making an auto-gpt concept for mistral/llama models? i haven't found one
Has anyone had success making an auto-gpt with any models? Besides toy use cases
Mistral AI Launches New 8x22B MOE Model
121–130 of 161 posts
Re: Mistral AI Launches New 8x22B MOE Model
#122has anyone had success making an auto-gpt concept for mistral/llama models? i haven't found one
Has anyone had success making an auto-gpt with any models? Besides toy use cases
I built one using GPT-4[1]. It's not perfect but is working quite well and is now being used by hundreds of users, apart from me, to work on real, non-toy tasks. For example, I used it to build most of a production-ready AWS infrastructure (and accompanying deploy script) with the AWS CDK.
I want to add Mistral support soon, probably via together.ai or a similar service.
Re: Mistral AI Launches New 8x22B MOE Model
#123Earlier quoted context omitted.
Has anyone had success making an auto-gpt with any models? Besides toy use cases
I built one using GPT-4[1]. It's not perfect but is working quite well and is now being used by hundreds of users, apart from me, to work on real, non-toy tasks. For example, I used it to build most of a production-ready AWS infrastructure (and accompanying deploy script) with the AWS CDK. I want to add Mistral support soon, probably via together.ai or a similar service. 1 - https://github.com/plandex-ai/plandex
Your link is broken.
Re: Mistral AI Launches New 8x22B MOE Model
#124Earlier quoted context omitted.
Has anyone had success making an auto-gpt with any models? Besides toy use cases
I built one using GPT-4[1]. It's not perfect but is working quite well and is now being used by hundreds of users, apart from me, to work on real, non-toy tasks. For example, I used it to build most of a production-ready AWS infrastructure (and accompanying deploy script) with the AWS CDK. I want to add Mistral support soon, probably via together.ai or a similar service. 1 - https://github.com/plandex-ai/plandex
Your link 404s fyi
Re: Mistral AI Launches New 8x22B MOE Model
#125Earlier quoted context omitted.
I built one using GPT-4[1]. It's not perfect but is working quite well and is now being used by hundreds of users, apart from me, to work on real, non-toy tasks. For example, I used it to build most of a production-ready AWS infrastructure (and accompanying deploy script) with the AWS CDK. I want to add Mistral support soon, probably via together.ai or a similar service. 1 - https://github.com/plandex-ai/plandex
Your link is broken.
Sorry, just fixed it.
Re: Mistral AI Launches New 8x22B MOE Model
#126What is the excitement around models that arent as good as llama?
This is clearly an inferior model that they are willing to share for marketing purposes.
If it was an improvement over llama, sure, but it seems like just an ad for bad AI.
Re: Mistral AI Launches New 8x22B MOE Model
#127Here is the unofficial benchmark: https://huggingface.co/mistral-community/Mixtral-8x22B-v0.1/...
Wish it had GPT-4, that’s the one to beat still.
It is there, not for all the benchmarks, but for those where it is included, GPT-4 scores much higher.
Not surprising since GPT-4 is still state-of-the-art and much bigger. Where Mistral has been particularly impressive is when you take the size of the model into account.
Re: Mistral AI Launches New 8x22B MOE Model
#128What is the excitement around models that arent as good as llama? This is clearly an inferior model that they are willing to share for marketing purposes. If it was an improvement over llama, sure, but it seems like just an ad for bad AI.
It beats llama on the benchmark posted below (though maybe leaked into training data). But also you can run it on cheaper split up hardware with less individual vram than the big llama.
Re: Mistral AI Launches New 8x22B MOE Model
#129What is the excitement around models that arent as good as llama? This is clearly an inferior model that they are willing to share for marketing purposes. If it was an improvement over llama, sure, but it seems like just an ad for bad AI.
What makes it you think it's not as good as LLaMA? It's likely much better. There are multiple open-weight models that are better than LLaMA 2 out there already.
Re: Mistral AI Launches New 8x22B MOE Model
#130Very important to note that this is a base model, not an instruct model. Instruct fine-tuned models are what's useful for chat.