CoolFace
Modelpublic

review-artifacts/nsdl-7b-rl-locus

sourceHugging Faceapache-2.0updated 4d agoView on Hugging Face
0likes14downloads
Model Card

NSDL 7B (SFT + RL), LOCUS: anonymized checkpoint for double-anonymous review

Row "Table 2: NSDL 7B (SFT + RL); Fig. 3" 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. Step-30 checkpoint of the RL run initialised from the NSDL 7B (SFT) LOCUS checkpoint (scripts/rlfinalsetting.sh). Provided for peer review only; do not redistribute during review. Author, affiliation and citation information is intentionally omitted.

FileBytessha256
added_tokens.json60558b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b
chat_template.json104994174d7176c52a7192f96fc34eb2cf23c7c2059d63cdbfadca1586ba89731fb7
config.json1541ccba9eb5596f73369f80d46f87b9725053c0e9abe4f09ccbef3b945be9a5a71e
generation_config.json26090e92cbc8634d6f5b1cb1ae58a3c48724a1ce1f11f8b7aecb5b9b3fd5d5a06bf
merges.txt16718538831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00004.safetensors5344827256f7d78ca2fca6902c22f2567818941cdb805dafb0dcda0072d7b2cde51274721f
model-00002-of-00004.safetensors4544503872a7934705cbbd58d521ee0407971ba33c658b32302cfc0a6d1ba8a5b850ac0cc8
model-00003-of-00004.safetensors5362477296fbd4d4941f9f95e49496acbe89093dcad4c904531779615be4429b6c9c140b4f
model-00004-of-00004.safetensors1332606112f50334aef9b3a86a47175bf19597e9569ce4b9999e9b4c7104c0d685cd4b8dcb
model.safetensors.index.json5761852ff41850df57394c9bebaa04c6ee9377ccedb2981b7dd1a4eb6d9995b83354d
preprocessor_config.json57110244222141516cc6ac28c41435d5ced7db23d352ce67ae588d5b248ccbc0b2f
special_tokens_map.json61376862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json1142199533624f49f1034c4f5d92e3ec47ccdf80ccd02caf1eb1d769872ba7fb1e5be112
tokenizer_config.json588551de45007c92099bcdd5a29b88fd0ee8766f1b3eba601aaed0edb1e42a63828a
vocab.json2776833ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910