alyakin314 commited on
Commit
a062df3
·
verified ·
1 Parent(s): c861aae

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +26 -2
README.md CHANGED
@@ -187,10 +187,34 @@ We used a two-stage curriculum:
187
  | Stage 1 | ~3.5 hours |
188
  | Stage 2 | ~30 minutes |
189
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
190
  ## Disclaimer
191
  Our work was performed and arXiv'ed in parallel with [LLaVA-NeXT-Med: Medical Multimodal Large Language Model](https://ieeexplore.ieee.org/document/10936400) by Yunfei Guo, Wu Huang. It is **NOT** the same model but trained in a very similar fashion. We chose to add clarifier *-OLAB* to ours to avoid confusion.
192
 
193
- ## BibTeX entry and citation info
194
 
195
  ```bibtex
196
  @article{alyakin2026cnsobsidian,
@@ -206,7 +230,7 @@ Our work was performed and arXiv'ed in parallel with [LLaVA-NeXT-Med: Medical Mu
206
  ```bibtex
207
  @misc{alyakin2025cnsobsidian-preprint,
208
  title={Repurposing the scientific literature with vision-language models},
209
- author={Anton Alyakin and Jaden Stryker and Daniel Alexander Alber and Karl L. Sangwon and Jin Vivian Lee and Brandon Duderstadt and Akshay Save and David Kurland and Spencer Frome and Shrutika Singh and Jeff Zhang and Eunice Yang and Ki Yun Park and Cordelia Orillac and Aly A. Valliani and Sean Neifert and Albert Liu and Aneek Patel and Christopher Livia and Darryl Lau and Ilya Laufer and Peter A. Rozman and Eveline Teresa Hidalgo and Howard Riina and Rui Feng and Todd Hollon and Yindalon Aphinyanaphongs and John G. Golfinos and Laura Snyder and Eric Leuthardt and Douglas Kondziolka and Eric Karl Oermann},
210
  year={2025},
211
  eprint={2502.19546},
212
  archivePrefix={arXiv},
 
187
  | Stage 1 | ~3.5 hours |
188
  | Stage 2 | ~30 minutes |
189
 
190
+ ## Technical Specifications
191
+
192
+ ### Model Architecture and Objective
193
+
194
+ See above.
195
+
196
+ ### Compute Infrastructure
197
+
198
+ NYU Langone’s UltraViolet HPC cluster.
199
+
200
+ #### Hardware
201
+
202
+ Training:
203
+ - 13 nodes × 8× NVIDIA H100 80GB = 104 GPUs total (via PyTorch FSDP)
204
+
205
+ Inference:
206
+ - 2× 80GB GPUs (A100/H100) (or analogous) for bfloat16 precision
207
+
208
+ #### Software
209
+
210
+ - Pytorch 2.4
211
+ - CUDA 12.1
212
+ - HuggingFace Transformers 4.44.0
213
+
214
  ## Disclaimer
215
  Our work was performed and arXiv'ed in parallel with [LLaVA-NeXT-Med: Medical Multimodal Large Language Model](https://ieeexplore.ieee.org/document/10936400) by Yunfei Guo, Wu Huang. It is **NOT** the same model but trained in a very similar fashion. We chose to add clarifier *-OLAB* to ours to avoid confusion.
216
 
217
+ ## Citation
218
 
219
  ```bibtex
220
  @article{alyakin2026cnsobsidian,
 
230
  ```bibtex
231
  @misc{alyakin2025cnsobsidian-preprint,
232
  title={Repurposing the scientific literature with vision-language models},
233
+ author={Anton Alyakin and Jaden Stryker and Daniel Alexander Alber and Karl L. Sangwon and Brandon Duderstadt and Akshay Save and David Kurland and Spencer Frome and Shrutika Singh and Jeff Zhang and Eunice Yang and Ki Yun Park and Cordelia Orillac and Aly A. Valliani and Sean Neifert and Albert Liu and Aneek Patel and Christopher Livia and Darryl Lau and Ilya Laufer and Peter A. Rozman and Eveline Teresa Hidalgo and Howard Riina and Rui Feng and Todd Hollon and Yindalon Aphinyanaphongs and John G. Golfinos and Laura Snyder and Eric Leuthardt and Douglas Kondziolka and Eric Karl Oermann},
234
  year={2025},
235
  eprint={2502.19546},
236
  archivePrefix={arXiv},