Table 2 Open-source LLM details
From: Benchmarking the diagnostic performance of open source LLMs in 1933 Eurorad case reports
Model | # Params | Base model | HuggingFace Link | Reference |
|---|---|---|---|---|
BioMistral-7B | 7B | Mistral-7B | ||
Gemma-2-27B | 27B | Gemma-2 | ||
Llama-2-70B | 70B | Llama-2 | ||
Medalpaca-13B | 13B | LLaMA | ||
Meditron-7B | 7B | Llama-2 | ||
Meta-Llama-3-8B | 8B | Llama-3 | https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-GGUF | |
Meta-Llama-3-70B | 70B | Llama-3 | https://huggingface.co/bartowski/Meta-Llama-3-70B-Instruct-GGUF | |
Mistral-Nemo | 12B | Mistral-Nemo | https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF | |
Mistral-Small | 22B | Mistral-Small | https://huggingface.co/bartowski/Mistral-Small-Instruct-2409-GGUF | |
Mixtral-8x7B | 46.7B | Mistral-7B | https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF | |
OpenBioLLM-Llama-3-8B | 8B | Llama-3 | ||
OpenBioLLM-Llama3-70B | 70B | Llama-3 | https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-GGUF | |
Phi-3-medium-128K | 14B | Phi-3 | https://huggingface.co/bartowski/Phi-3-medium-128k-instruct-GGUF | |
Qwen2.5-32B | 32B | Qwen-2.5 | https://qwenlm.github.io/blog/qwen2.5/ & https://arxiv.org/abs/2407.10671 | |
Vicuna-13B | 13B | Llama-2 |
