Instructions to use RomanCohort/RNAQwen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RomanCohort/RNAQwen with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("RomanCohort/RNAQwen", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download reports/batch_sweep_long.json from RomanCohort/RNAQwen: direct link, hf CLI and curl.
- Browser
- Download file 1.06 kB
-
https://huggingface.co/RomanCohort/RNAQwen/resolve/main/reports/batch_sweep_long.json
- Command line
-
hf download hf://RomanCohort/RNAQwen/reports/batch_sweep_long.json
-
curl -L -o batch_sweep_long.json https://huggingface.co/RomanCohort/RNAQwen/resolve/main/reports/batch_sweep_long.json
1.06 kB
| { | |
| "batches": { | |
| "1": { | |
| "sec_per_step_median": 4.0073, | |
| "sec_per_step_mean": 4.0064, | |
| "sec_per_sample": 4.0073, | |
| "samples_per_sec": 0.25, | |
| "speedup_vs_batch1": 1.0, | |
| "peak_mem_GiB": 31.58, | |
| "max_rna_nt_in_batch": 1022, | |
| "steps": 3 | |
| }, | |
| "2": { | |
| "sec_per_step_median": 8.504, | |
| "sec_per_step_mean": 8.4372, | |
| "sec_per_sample": 4.252, | |
| "samples_per_sec": 0.235, | |
| "speedup_vs_batch1": 0.942, | |
| "peak_mem_GiB": 48.93, | |
| "max_rna_nt_in_batch": 1022, | |
| "steps": 3 | |
| }, | |
| "4": { | |
| "sec_per_step_median": 20.2776, | |
| "sec_per_step_mean": 20.2452, | |
| "sec_per_sample": 5.0694, | |
| "samples_per_sec": 0.197, | |
| "speedup_vs_batch1": 0.79, | |
| "peak_mem_GiB": 90.65, | |
| "max_rna_nt_in_batch": 1022, | |
| "steps": 3 | |
| } | |
| }, | |
| "data": "C:\\qwen-api\\RNAQwen\\data\\processed\\rnaqa_rnacentral_all.jsonl", | |
| "n_samples": 1121, | |
| "device": "AMD Radeon(TM) 8060S Graphics", | |
| "mem_total_GiB": 99.74, | |
| "grad_checkpointing": true | |
| } |