We lifted 13 functions out of this paper's own repositories and ran 8 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| mediabrain-sjtu/ming | canonical | 3 of 3 |
| mediabrain-sjtu/medicalgpt-zh | pwc_unofficial | 5 of 10 |
| Function | Status | Where it lives |
|---|---|---|
| check_target_module_exists | Ran | mediabrain-sjtu/medicalgpt-zh/ming/model/utils.py code served (permissive licence) · get_code("ce4b943c1f4622e6") |
| convert_to_json | Ran | mediabrain-sjtu/medicalgpt-zh/ming/eval/eval_gpt4.py code served (permissive licence) · get_code("f315af9021bb4de9") |
| get_chunk | Ran | mediabrain-sjtu/medicalgpt-zh/ming/eval/model_diverse_gen.py code served (permissive licence) · get_code("42a46570620cd9fa") |
| get_model_name_from_path | Ran | mediabrain-sjtu/medicalgpt-zh/ming/utils.py code served (permissive licence) · get_code("fa6d2859d3461c9e") |
| normalize | Ran | mediabrain-sjtu/ming/ming/eval/eval_em.py code served (permissive licence) · get_code("0133c7875f5508e2") |
| normalize_dfrac | Ran | mediabrain-sjtu/ming/ming/eval/eval_em.py code served (permissive licence) · get_code("ceb9b19eaecb1183") |
| normalize_frac | Ran | mediabrain-sjtu/ming/ming/eval/eval_em.py code served (permissive licence) · get_code("75cb6a84ff49f59b") |
| split_list | Ran | mediabrain-sjtu/medicalgpt-zh/ming/eval/model_diverse_gen.py code served (permissive licence) · get_code("076c252c52cbb161") |
| create_data_loader | Not yet run | mediabrain-sjtu/medicalgpt-zh/ming/eval/model_diverse_gen.py code served (permissive licence) · get_code("8948016310b7f832") |
| create_mixoflora_module | Not yet run | mediabrain-sjtu/medicalgpt-zh/ming/model/utils.py code served (permissive licence) · get_code("ff08a7b61f0ff773") |
| get_default_conv_template | Not yet run | mediabrain-sjtu/medicalgpt-zh/ming/conversations.py code served (permissive licence) · get_code("6f3e31642958b2ee") |
| get_mixoflora_model | Not yet run | mediabrain-sjtu/medicalgpt-zh/ming/model/utils.py code served (permissive licence) · get_code("80d3d94e5c8311ac") |
| load_pretrained_model | Not yet run | mediabrain-sjtu/medicalgpt-zh/ming/model/builder.py code served (permissive licence) · get_code("e9663a782ec03800") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Large language models like ChatGPT have shown substantial progress in natural language understanding and generation, proving valuable across various disciplines, including the medical field. Despite advancements, challenges persist due to the complexity and diversity inherent in medical tasks which often require multi-task learning capabilities. Previous approaches, although beneficial, fall short in real-world applications because they necessitate task-specific annotations at inference time, limiting broader generalization. This paper introduces MING-MOE, a novel Mixture-of-Expert~(MOE)-based medical large language model designed to manage diverse and complex medical tasks without requiring task-specific annotations, thus enhancing its usability across extensive datasets. MING-MOE employs a Mixture of Low-Rank Adaptation (MoLoRA) technique, allowing for efficient parameter usage by maintaining base model parameters static while adapting through a minimal set of trainable parameters. We demonstrate that MING-MOE achieves state-of-the-art (SOTA) performance on over 20 medical tasks, illustrating a significant improvement over existing models. This approach not only extends the capabilities of medical language models but also improves inference efficiency.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2404.09027")
get_code_for_paper("2404.09027")
have("2404.09027")
Connect an agent — have() is free.