Phi-4-11B
Данная модель представляет собой обрезанный вариант Phi-4, сжатый с помощью СНАЙПЕРА (бумага). LoRA точно настроен на 2000 образцов...
Данная модель представляет собой обрезанный вариант Phi-4, сжатый с помощью СНАЙПЕРА (бумага). LoRA точно настроен на 2000 образцов...
PEFT LoRA adapter that specializes LiquidAI/LFM2.5-1.2B-Instruct for marketing workflows (trained via Unsloth hub id unsloth/LFM2.5-1.2B-Instruct). Tanpo is a...
— Developed by: [More Information Needed] — Funded by [optional]: [More Information Needed] — Shared by [optional]: [More...
— Developed by: [More Information Needed] — Funded by [optional]: [More Information Needed] — Shared by [optional]: [More...
Agent-style chat model obtained by LoRA fine-tuning openbmb/MiniCPM5-2B (2.57B parameters, Llama architecture, 130,560-token vocabulary) on agent traces from...
Training loss over the run (representative logged steps): 0.9714 -> 0.5867 -> 0.5562. Smooth, monotonic decline consistent with...
Held-out loss: 0.696 (epoch 0.2) -> 0.651 (0.6) -> 0.622 (epoch 2). Training loss ended at about 0.55....
> Behavioral release candidate — not promoted. The checkpoint-5001448 > files are structurally corrected and load successfully, but...
— Developed by: [More Information Needed] — Funded by [optional]: [More Information Needed] — Shared by [optional]: [More...
The original BF16 release had extra wrapper prefixes in its Safetensors headers and index. Stock loaders could therefore...