TimeCapsuleLLM: LLM trained only on data from 1800-1875
1–10 of 334 posts
Re: TimeCapsuleLLM: LLM trained only on data from 1800-1875
#2Would be interesting to train a cutting edge model with a cut off date of say 1900 and then prompt it about QM and relativity with some added context.
If the model comes up with anything even remotely correct it would be quite a strong evidence that LLMs are a path to something bigger if not then I think it is time to go back to the drawing board.
Re: TimeCapsuleLLM: LLM trained only on data from 1800-1875
#3Would be interesting to train a cutting edge model with a cut off date of say 1900 and then prompt it about QM and relativity with some added context. If the model comes up with anything even remotely correct it would be quite a strong evidence that LLMs are a path to something bigger if not then I think it is time to go back to the drawing board.
yeah i was just wondering that. i wonder how much stem material is in the training set...
Re: TimeCapsuleLLM: LLM trained only on data from 1800-1875
#4Anyone seen a low-friction way to run prompts through this yet, either via a hosted API or chat UI or a convenient GGML or MLX build that runs in Ollama or llama.cpp or LM Studio?
Re: TimeCapsuleLLM: LLM trained only on data from 1800-1875
#5Anyone seen a low-friction way to run prompts through this yet, either via a hosted API or chat UI or a convenient GGML or MLX build that runs in Ollama or llama.cpp or LM Studio?
+1
Re: TimeCapsuleLLM: LLM trained only on data from 1800-1875
#6Exciting idea!
Re: TimeCapsuleLLM: LLM trained only on data from 1800-1875
#7This will be something good - would love something on Ollama or lmstudio.
Re: TimeCapsuleLLM: LLM trained only on data from 1800-1875
#8Anyone seen a low-friction way to run prompts through this yet, either via a hosted API or chat UI or a convenient GGML or MLX build that runs in Ollama or llama.cpp or LM Studio?
Not a direct answer but it looks like v0.5 is a nanoGPT arch and v1 is a Phi 1.5 arch, which should be well supported by quanting utilities for any engine. They are small too and should be able to be done on a potato.
Re: TimeCapsuleLLM: LLM trained only on data from 1800-1875
#9Would be interesting to train a cutting edge model with a cut off date of say 1900 and then prompt it about QM and relativity with some added context. If the model comes up with anything even remotely correct it would be quite a strong evidence that LLMs are a path to something bigger if not then I think it is time to go back to the drawing board.
I suppose the vast majority of training data used for cutting edge models was created after 1900.
Re: TimeCapsuleLLM: LLM trained only on data from 1800-1875
#10Would be interesting to train a cutting edge model with a cut off date of say 1900 and then prompt it about QM and relativity with some added context. If the model comes up with anything even remotely correct it would be quite a strong evidence that LLMs are a path to something bigger if not then I think it is time to go back to the drawing board.
yeah i was just wondering that. i wonder how much stem material is in the training set...
i will go for ‘aint gonna happen for a 1000 dollars alex’