modrill

rstar_coder_32m_lora_olmo3_1025_7b_base

README

License: apache-2.0

Immutable LoRA adapter freeze (ADAPTER_ONLY_NO_MERGE).

Base: allenai/Olmo-3-1025-7B @ a81bae42db3975be1671e27b9c9a56da1a9f980f
Adapter tree SHA-256: 4964d87b49be67f1b80a626c5ded0c482c69553ec6799eda2d073e0f8e9e2569
Immutable tag: freeze-4964d87b49be67f1
Dose: 32018321 assistant target tokens (step 419)
Recipe SHA-256: b2fb6275575e08e1b07d482d9f12418b22f5588c55b28bbf9dec29fb3e1fadf9
Data READY manifest SHA-256: 397e8ba94a5d421ee960344e3e45e431ea90174ff9c0e459f5d9bb57137caf97
DEV256 (seed 3407): pass@1 = 0.2734375 (70/256)
Trained on GPU: 1

Do not merge unless you intentionally create a separate merged revision. Load with PEFT against the pinned base revision above.

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Model Details

Model Provider

modrill

Model Tree

Base

allenai/Olmo-3-1025-7B

Adapter

this model

Input Modalities

Text

Output Modalities

Text

Supported Functionality

Dedicated Endpoints

License: apache-2.0

Immutable LoRA adapter freeze (ADAPTER_ONLY_NO_MERGE).

Base: allenai/Olmo-3-1025-7B @ a81bae42db3975be1671e27b9c9a56da1a9f980f
Adapter tree SHA-256: 4964d87b49be67f1b80a626c5ded0c482c69553ec6799eda2d073e0f8e9e2569
Immutable tag: freeze-4964d87b49be67f1
Dose: 32018321 assistant target tokens (step 419)
Recipe SHA-256: b2fb6275575e08e1b07d482d9f12418b22f5588c55b28bbf9dec29fb3e1fadf9
Data READY manifest SHA-256: 397e8ba94a5d421ee960344e3e45e431ea90174ff9c0e459f5d9bb57137caf97
DEV256 (seed 3407): pass@1 = 0.2734375 (70/256)
Trained on GPU: 1

Do not merge unless you intentionally create a separate merged revision. Load with PEFT against the pinned base revision above.