We lifted 14 functions out of this paper's own repositories and ran 13 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 |
|---|---|---|
| freedomintelligence/huatuogpt-ii | canonical | 13 of 14 |
| Function | Status | Where it lives |
|---|---|---|
| deduplicate | Ran | freedomintelligence/huatuogpt-ii/evaluation/eval_huatuo_inst.py pointer only (licence: NONE) · get_code("1c39574f5e470abf") |
| filter_str | Ran | freedomintelligence/huatuogpt-ii/adaption/data_unification/rewrite.py pointer only (licence: NONE) · get_code("13ebc20073fe384f") |
| generate_prompt | Ran | freedomintelligence/huatuogpt-ii/cli_demo.py pointer only (licence: NONE) · get_code("baa2dd07a544df5c") |
| get_data_query | Ran | freedomintelligence/huatuogpt-ii/adaption/data_unification/rewrite.py pointer only (licence: NONE) · get_code("dbd2112d465a82e2") |
| get_response | Ran | freedomintelligence/huatuogpt-ii/evaluation/eval_qa.py pointer only (licence: NONE) · get_code("0cc6223401defc70") |
| match_choice | Ran | freedomintelligence/huatuogpt-ii/evaluation/scorer.py pointer only (licence: NONE) · get_code("3da76bec93a6ae0c") |
| match_choice2 | Ran | freedomintelligence/huatuogpt-ii/evaluation/scorer.py pointer only (licence: NONE) · get_code("3e574889ab383717") |
| match_choice3 | Ran | freedomintelligence/huatuogpt-ii/evaluation/scorer.py pointer only (licence: NONE) · get_code("c0faf671597614bb") |
| ngram_jaccard_score | Ran | freedomintelligence/huatuogpt-ii/adaption/data_unification/rewrite.py pointer only (licence: NONE) · get_code("2af3169badbc6691") |
| parse_classification_cot | Ran | freedomintelligence/huatuogpt-ii/evaluation/eval_huatuo_conv.py pointer only (licence: NONE) · get_code("afe2c8247569f6e0") |
| remove_overlap | Ran | freedomintelligence/huatuogpt-ii/cli_demo.py pointer only (licence: NONE) · get_code("3bc9437adf1d7ea1") |
| table_to_csv_string | Ran | freedomintelligence/huatuogpt-ii/evaluation/eval_qa.py pointer only (licence: NONE) · get_code("4b9933d832571ead") |
| transfer_conv | Ran | freedomintelligence/huatuogpt-ii/evaluation/eval_huatuo_conv.py pointer only (licence: NONE) · get_code("e420c2ab67f141f8") |
| load_model | Not yet run | freedomintelligence/huatuogpt-ii/cli_demo.py pointer only (licence: NONE) · get_code("719c8f0c667de29a") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Adapting a language model into a specific domain, a.k.a `domain adaption', is a common practice when specialized knowledge, e.g. medicine, is not encapsulated in a general language model like Llama2. The challenge lies in the heterogeneity of data across the two training stages, as it varies in languages, genres, or formats. To tackle this and simplify the learning protocol, we propose to transform heterogeneous data, from the both pre-training and supervised stages, into a unified, simple input-output pair format. We validate the new protocol in the domains where proprietary LLMs like ChatGPT perform relatively poorly, such as Traditional Chinese Medicine. The developed model, HuatuoGPT-II, has shown state-of-the-art performance in Chinese medicine domain on a number of benchmarks, e.g. medical licensing exams. It even outperforms proprietary models like ChatGPT and GPT-4 in some aspects, especially in Traditional Chinese Medicine. Expert manual evaluations further validate HuatuoGPT-II's advantages over existing LLMs. Notably, HuatuoGPT-II was benchmarked in a fresh Chinese National Medical Licensing Examination where it achieved the best performance, showcasing not only its effectiveness but also its generalization capabilities.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2311.09774")
get_code_for_paper("2311.09774")
have("2311.09774")
Connect an agent — have() is free.