Open Issues Need Help
View All on GitHub help wanted
nokia-applied-research/AnyJev nokia-applied-research/AnyJev Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating)
Open project →
356
Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating)
Python
#calibration#decision-model#jev#jev-model#llm#system-one#transformers#vllm
help wanted
nokia-applied-research/AnyJev nokia-applied-research/AnyJev Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating)
Open project →
356
Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating)
Python
#calibration#decision-model#jev#jev-model#llm#system-one#transformers#vllm
anyjev/backends/llamacpp.py`: a `LlamaCppBackend` that loads a GGUF model in-process through `llama-cpp-python` and implements `next_token_logprobs` only. about 1 month ago
help wanted
nokia-applied-research/AnyJev nokia-applied-research/AnyJev Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating)
Open project →
356
Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating)
Python
#calibration#decision-model#jev#jev-model#llm#system-one#transformers#vllm