Instructions to use blazeofchi/mempool-qwen3-0p6b-logits-orchestrator-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use blazeofchi/mempool-qwen3-0p6b-logits-orchestrator-v1 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("blazeofchi/mempool-qwen3-0p6b-logits-orchestrator-v1", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "device": "cuda", | |
| "history": [ | |
| { | |
| "epoch": 0, | |
| "loss": 3.11750134399959 | |
| }, | |
| { | |
| "epoch": 1, | |
| "loss": 2.809019318648747 | |
| }, | |
| { | |
| "epoch": 2, | |
| "loss": 2.8290022100721086 | |
| }, | |
| { | |
| "epoch": 3, | |
| "loss": 2.817454559462411 | |
| }, | |
| { | |
| "epoch": 4, | |
| "loss": 2.805349017892565 | |
| }, | |
| { | |
| "epoch": 5, | |
| "loss": 2.7349614586148943 | |
| }, | |
| { | |
| "epoch": 6, | |
| "loss": 2.7246988671166554 | |
| }, | |
| { | |
| "epoch": 7, | |
| "loss": 2.7136061021259854 | |
| }, | |
| { | |
| "epoch": 8, | |
| "loss": 2.687513675008501 | |
| }, | |
| { | |
| "epoch": 9, | |
| "loss": 2.7999841826302663 | |
| }, | |
| { | |
| "epoch": 10, | |
| "loss": 2.7054038047790527 | |
| }, | |
| { | |
| "epoch": 11, | |
| "loss": 2.659690465245928 | |
| }, | |
| { | |
| "epoch": 12, | |
| "loss": 2.848549485206604 | |
| }, | |
| { | |
| "epoch": 13, | |
| "loss": 2.659048242228372 | |
| }, | |
| { | |
| "epoch": 14, | |
| "loss": 2.6345216717038835 | |
| }, | |
| { | |
| "epoch": 15, | |
| "loss": 2.6133223516600474 | |
| }, | |
| { | |
| "epoch": 16, | |
| "loss": 2.5888123171670094 | |
| }, | |
| { | |
| "epoch": 17, | |
| "loss": 2.580440470150539 | |
| }, | |
| { | |
| "epoch": 18, | |
| "loss": 2.6477542349270413 | |
| }, | |
| { | |
| "epoch": 19, | |
| "loss": 2.6182081358773366 | |
| }, | |
| { | |
| "epoch": 20, | |
| "loss": 2.5893647926194325 | |
| }, | |
| { | |
| "epoch": 21, | |
| "loss": 2.591572182519095 | |
| }, | |
| { | |
| "epoch": 22, | |
| "loss": 2.5323841656957353 | |
| }, | |
| { | |
| "epoch": 23, | |
| "loss": 2.544121095112392 | |
| }, | |
| { | |
| "epoch": 24, | |
| "loss": 2.5288875699043274 | |
| }, | |
| { | |
| "epoch": 25, | |
| "loss": 2.5025893364633833 | |
| }, | |
| { | |
| "epoch": 26, | |
| "loss": 2.603824121611459 | |
| }, | |
| { | |
| "epoch": 27, | |
| "loss": 2.543979917253767 | |
| }, | |
| { | |
| "epoch": 28, | |
| "loss": 2.4952145644596646 | |
| }, | |
| { | |
| "epoch": 29, | |
| "loss": 2.539324470928737 | |
| }, | |
| { | |
| "epoch": 30, | |
| "loss": 2.5138033287865773 | |
| }, | |
| { | |
| "epoch": 31, | |
| "loss": 2.4722729665892467 | |
| }, | |
| { | |
| "epoch": 32, | |
| "loss": 2.408249352659498 | |
| }, | |
| { | |
| "epoch": 33, | |
| "loss": 2.4780009303774153 | |
| }, | |
| { | |
| "epoch": 34, | |
| "loss": 2.4572549717766896 | |
| }, | |
| { | |
| "epoch": 35, | |
| "loss": 2.393418550491333 | |
| }, | |
| { | |
| "epoch": 36, | |
| "loss": 2.4449552042143687 | |
| }, | |
| { | |
| "epoch": 37, | |
| "loss": 2.616686258997236 | |
| }, | |
| { | |
| "epoch": 38, | |
| "loss": 2.4797831092561995 | |
| }, | |
| { | |
| "epoch": 39, | |
| "loss": 2.474162220954895 | |
| } | |
| ], | |
| "output_dir": "research/models/20260628-qwen3-0p6b-logits-orchestrator-full-gpu-l40s", | |
| "record_count": 53, | |
| "schema_version": "mempool.qwen_logits_orchestrator_train_report.v1", | |
| "worker_ids": [ | |
| "ollama-cloud-deepseek-v4-pro", | |
| "ollama-cloud-glm-5.2", | |
| "ollama-cloud-kimi-k2.7-code", | |
| "ollama-cloud-qwen3-coder-480b" | |
| ], | |
| "workflow_labels": [ | |
| "direct", | |
| "verify_then_fallback" | |
| ], | |
| "base_model": "Qwen/Qwen3-0.6B" | |
| } | |