GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
review-artifacts
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
review-artifacts
Model Tree
Qwen/Qwen2.5-VL-3B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Row "Table 2: NSDL 3B (SFT)" of the submission. Weights are stored in bfloat16, the dtype the
evaluation loader uses. Load and run with the code in the anonymized repository
linked from the paper (nsdl/ + scripts/eval_lnsdl_agentic_viki_l2.py);
evaluation flags are in that repository's README.
Trained on the LOCUS train split with the VLM input capped at 524288 pixels (seed 1234).
Provided for peer review only; do not redistribute during review. Author,
affiliation and citation information is intentionally omitted.
| File | Bytes | sha256 |
|---|---|---|
added_tokens.json | 605 | 58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b |
chat_template.json | 1049 | 94174d7176c52a7192f96fc34eb2cf23c7c2059d63cdbfadca1586ba89731fb7 |
config.json | 1540 | 236e39592c9ba9eb4db6ef70b7df4eb9201eebae234b6f8e915d461c0ee18ad9 |
generation_config.json | 290 | d04905081373c40b5cf0dc0ab432c879b8312bea794b1fd14c4c8828054d1409 |
merges.txt | 1671853 | 8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 |
model-00001-of-00002.safetensors | 5351163000 | 02169e25a681f014f1da9b1f973712103e35163e00da91f6556a9cdad2b12c8d |
model-00002-of-00002.safetensors | 2780505008 | 1e1b7f9d4b390c3da7d04a5bbdd6b40ad05a658a80ac9ec6a9a16d9197a80280 |
model.safetensors.index.json | 65505 | 37521b6b34cd7a6c8fcdda655a14fc648722a5ec110788179d1d55847ba5ac45 |
preprocessor_config.json | 571 | 10244222141516cc6ac28c41435d5ced7db23d352ce67ae588d5b248ccbc0b2f |
special_tokens_map.json | 613 | 76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd |
tokenizer.json | 11421995 | 33624f49f1034c4f5d92e3ec47ccdf80ccd02caf1eb1d769872ba7fb1e5be112 |
tokenizer_config.json | 7300 | c182cc5f590489eba7c5435864b0814fcd9256ef72933f8ccc142116974dbb01 |
vocab.json | 2776833 | ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 |