Hugging Face's logo

disi-unibo-nlp
/
MedGENIE-fid-flan-t5-base-medqa

Question Answering
Transformers
PyTorch
English
t5
text2text-generation
medical
fusion-in-decoder
text-generation-inference
Inference Endpoints
Model card Files Community
alecocc commited on
Commit
4ea418f
•
1 Parent(s): 793a2fb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -78,7 +78,7 @@ At the time of release, MedGENIE-fid-flan-t5-base-medqa is a new lightweight SOT
78
  | Mistral-Instruct | R (MedWiki) | 2-shot | 7B | 45.1 |
79
  | Galactica | ∅ | 0-shot | 120B | 44.4 |
80
  | LLaMA-2 <small>([Liévin et al.](https://arxiv.org/abs/2207.08143))</small> | &empty; | 0-shot | 70B | 43.4 |
81
- | BioReader <small>(Frisoni et al.)</small> | R (PubMed-RCT) | Fine-tuned | 230M | 43.0 |
82
  | Guanaco <small>([Liévin et al.](https://arxiv.org/abs/2207.08143))</small> | &empty; | 0-shot | 33B | 42.9 |
83
  | LLaMA-2-chat <small>([Liévin et al.](https://arxiv.org/abs/2207.08143))</small> | &empty; | 0-shot | 70B | 42.3 |
84
  | Vicuna 1.5 <small>([Liévin et al.](https://arxiv.org/abs/2207.08143))</small> | &empty; | 0-shot | 65B | 41.6 |
@@ -87,13 +87,13 @@ At the time of release, MedGENIE-fid-flan-t5-base-medqa is a new lightweight SOT
87
  | Guanaco <small>([Liévin et al.](https://arxiv.org/abs/2207.08143))</small> | &empty; | 0-shot | 65B | 40.8 |
88
  | Falcon-Instruct <small>([Liévin et al.](https://arxiv.org/abs/2207.08143))</small> | &empty; | 0-shot | 40B | 39.0 |
89
  | Vicuna 1.3 <small>([Liévin et al.](https://arxiv.org/abs/2207.08143))</small> | &empty; | 0-shot | 13B | 38.7 |
90
- | GreaseLM <small>(Zhang et al.)</small> | R (UMLS) | Fine-tuned | 359M | 38.5 |
91
  | PubMedBERT <small>([Singhal et al.](https://arxiv.org/abs/2212.13138))</small> | &empty; | Fine-tuned | 110M | 38.1 |
92
- | QA-GNN <small>(Yasunaga et al.)</small> | R (UMLS) | Fine-tuned | 360M | 38.0 |
93
  | LLaMA-2 <small>([Yang et al.](https://arxiv.org/abs/2309.02233))</small> | R (Wikipedia) | k-shot | 13B | 37.6 |
94
  | LLaMA-2-chat | R (MedWiki) | 2-shot | 7B | 37.2 |
95
  | LLaMA-2-chat | &empty; | 2-shot | 7B | 37.2 |
96
- | BioBERT <small>(Lee et al.)</small> | &empty; | Fine-tuned | 110M | 36.7 |
97
  | MTP-Instruct <small>([Liévin et al.](https://arxiv.org/abs/2207.08143))</small> | &empty; | 0-shot | 30B | 35.1 |
98
  | GPT-Neo <small>([Singhal et al.](https://arxiv.org/abs/2212.13138))</small> | &empty; | Fine-tuned | 2.5B | 33.3 |
99
  | LLaMa-2-chat <small>([Liévin et al.](https://arxiv.org/abs/2207.08143))</small> | &empty; | 0-shot | 13B | 32.2 |
 
78
  | Mistral-Instruct | R (MedWiki) | 2-shot | 7B | 45.1 |
79
  | Galactica | &empty; | 0-shot | 120B | 44.4 |
80
  | LLaMA-2 <small>([Liévin et al.](https://arxiv.org/abs/2207.08143))</small> | &empty; | 0-shot | 70B | 43.4 |
81
+ | BioReader <small>([Frisoni et al.](https://aclanthology.org/2022.emnlp-main.390/))</small> | R (PubMed-RCT) | Fine-tuned | 230M | 43.0 |
82
  | Guanaco <small>([Liévin et al.](https://arxiv.org/abs/2207.08143))</small> | &empty; | 0-shot | 33B | 42.9 |
83
  | LLaMA-2-chat <small>([Liévin et al.](https://arxiv.org/abs/2207.08143))</small> | &empty; | 0-shot | 70B | 42.3 |
84
  | Vicuna 1.5 <small>([Liévin et al.](https://arxiv.org/abs/2207.08143))</small> | &empty; | 0-shot | 65B | 41.6 |
 
87
  | Guanaco <small>([Liévin et al.](https://arxiv.org/abs/2207.08143))</small> | &empty; | 0-shot | 65B | 40.8 |
88
  | Falcon-Instruct <small>([Liévin et al.](https://arxiv.org/abs/2207.08143))</small> | &empty; | 0-shot | 40B | 39.0 |
89
  | Vicuna 1.3 <small>([Liévin et al.](https://arxiv.org/abs/2207.08143))</small> | &empty; | 0-shot | 13B | 38.7 |
90
+ | GreaseLM <small>([Zhang et al.](https://arxiv.org/abs/2201.08860))</small> | R (UMLS) | Fine-tuned | 359M | 38.5 |
91
  | PubMedBERT <small>([Singhal et al.](https://arxiv.org/abs/2212.13138))</small> | &empty; | Fine-tuned | 110M | 38.1 |
92
+ | QA-GNN <small>([Yasunaga et al.](https://arxiv.org/abs/2104.06378))</small> | R (UMLS) | Fine-tuned | 360M | 38.0 |
93
  | LLaMA-2 <small>([Yang et al.](https://arxiv.org/abs/2309.02233))</small> | R (Wikipedia) | k-shot | 13B | 37.6 |
94
  | LLaMA-2-chat | R (MedWiki) | 2-shot | 7B | 37.2 |
95
  | LLaMA-2-chat | &empty; | 2-shot | 7B | 37.2 |
96
+ | BioBERT <small>([Lee et al.](https://arxiv.org/abs/1901.08746))</small> | &empty; | Fine-tuned | 110M | 36.7 |
97
  | MTP-Instruct <small>([Liévin et al.](https://arxiv.org/abs/2207.08143))</small> | &empty; | 0-shot | 30B | 35.1 |
98
  | GPT-Neo <small>([Singhal et al.](https://arxiv.org/abs/2212.13138))</small> | &empty; | Fine-tuned | 2.5B | 33.3 |
99
  | LLaMa-2-chat <small>([Liévin et al.](https://arxiv.org/abs/2207.08143))</small> | &empty; | 0-shot | 13B | 32.2 |