Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
s3nh 
posted an update Jan 21
Post
GPU Poor POV: My storytelling choices of the week

Its end of the week, I decided to summarize my observations in community based LLMs and mention few models in specific area which are very interesting and has capability to create some insightful stories despite of its relatively lightweight form.

I personally did not use LLMs in my daily routine to tasks like function calling, parsing or assist in code writing. What I tried to use for is storytelling, because it always amaze me how different these models comes to different preferred tasks.

How this model are able to generalize the stories and sometimes, how high level of creativity they carry.

BlueNipples/DaringLotus-v2-10.7b its main target is to generate prose. Quoting the author 'It shares it's good prose, and relatively decent coherency, being a little bit more on the side of prose, and a little bit less on the side of coherency. I like this model for generating great prose if I feel like regening a bit. '

https://huggingface.co/NeuralNovel/Aeryth-7B-v0.1
great work by @NeuralNovel , I really like how flexible this model is, there is no strict focus on a certain role, so definitely worth a try. Would love to hear more about dataset on which was trained, afaik is private rn. best suited for Science Fiction, History & Romance genres due to the training data used.

And the last one for today is FPHam/Sydney_Pirate_Mistral_7b @FPHam work always amaze me how the models are able to stick to provided role. awesome work as always, Ill for sure use this model to generate some interesting stories.

I know that hype train is going fast but as I observe people here on huggingface are creating really creative models which are for sure worth to try. Have a great day <3

I didn't dive deeply into all the creative role play models, although I sense there is a great deal of innovation happening there, unrecognized. Beautiful art!

Thank you for reviewing these models, I need to give DaringLotus and Sydney_Pirate a spin they look great!

Amazing Thanks for sharing!
I've found that using llms that are proficient in roleplaying for their specific task are best to use in multi agent workflows.

Curious to try inference on some of these and test how whether their 'personalities' persist over long contexts. If not extending the context further should be straightforward.

Also very curious how the consequences of merging various roleplay models will affect them
Will their personalities change?
Develop new personalities?
Perhaps they keep all personalities
Or all of the above.

As a finishing thought I believe RP is one of the keys to unlocking better performance and interpretability within LLMs, Multimodal LLMs. I believe for a safe AI future all AI should be NOT censored, opensourced and available however when deploying an llm in public to users that may be sensitive such as users under 18, it is important to be aware of the sources of a particular model tree
An resource to do that is: https://huggingface.co/spaces/mrfakename/merge-model-tree

I would also like to highlight this paper:
Sleeper Agents: Training Deceptive LLMs that persist Through Safety Training https://huggingface.co/papers/2401.05566

·

Thanks! The interesting thing is that many rp models comes from merging process, and its behaviour differ significantly than its behaviour on base model. i am also curious about the inference on longer context, and what is the point (proper lenght) when the personality starts to dissapear? These are really interesting points.

I have to extend my thought in next posts and provide it with some technical details. Your feedback and thinking process is amazing, thank you very much <3

Thank you @s3nh this is exactly what a friend of mine needed to know! Forwarding him your post

I'm amazed that you are amazed.

·

Curated Information is amazing