Aller au contenu
ModelPrésentéExterne
Télécharger

OneReason 0.8B Frontier SFT Epoch1

One epoch local LoRA SFT on frontierfeedbackcorelistwiseinvariantv1.

Sourcehuggingface.co/reimu996/OneReason-0.8B-Frontier-SFT-Epoch1/tree/10cfbae7470ccbeee1bb2eb5cb117741cca1e5e0
TypeOtherModèle de baseOpenOneRec/OneReason-0.8B-pretrain-competitionVersionRevision 10cfbaeCClasse

Source du modèle

Type
Other
Taille du fichier
77,0 MB
Modèle de base
OpenOneRec/OneReason-0.8B-pretrain-competition
Version
vRevision 10cfbae
Mis à jour
27 oct. 2026
Téléchargements
5
Source
Hugging Face

Description de la source

OneReason-0.8B Frontier FeedbackCore SFT LoRA

One epoch local LoRA SFT on frontier_feedbackcore_listwise_invariant_v1.

The repository contains the LoRA adapter and its configuration. Load it together with the clean OneReason-0.8B competition base model; it is not a full model.

Training data: 63,700 records from the frontier feedbackcore candidate.

Configuration: LoRA rank 32, alpha 32, dropout 0.05, BF16, learning rate 2e-4, gradient accumulation 8, requested cutoff length 16,384, and one epoch.

Sources

1 source
Hugging FacePrincipalVersion 10cfbae7470ccbeee1bb2eb5cb117741cca1e5e0
huggingface.co/reimu996/OneReason-0.8B-Frontier-SFT-Epoch1/tree/10cfbae7470ccbeee1bb2eb5cb117741cca1e5e0

Vérifié 27 oct.

Artefacts du modèle

1 artefact

adapter_model.safetensors

safetensors · 77,0 MB · SHA-256 eec36e9cfcea…f041 · Hugging Face

Download file

Extraits de sources

3 extraits
Readme8 aoûthuggingface.co/reimu996/OneReason-0.8B-Frontier-SFT-Epoch1

--- base_model: OpenOneRec/OneReason-0.8B-pretrain-competition library_name: peft pipeline_tag: text-generation tags: - lora - kuaishou-llmrec - frontier-feedbackcore --- # OneReason-0.8B Frontier FeedbackCore SFT LoRA One epoch local LoRA SFT on `frontier_feedbackcore_listwise_invariant_v1`. The repository contains the LoRA adapter and its configuration. Load it together with the clean OneReason-0.8B competition base model; it is not a full model. Training data: 63,700 records from the frontier feedbackcore candidate. Configuration: LoRA rank 32, alpha 32, dropout 0.05, BF16, learning rate 2e-4, gradient accumulation 8, requested cutoff length 16,384, and one epoch.

Note27 oct.huggingface.co/reimu996/OneReason-0.8B-Frontier-SFT-Epoch1

Source context: 5 downloads · 0 likes · Pipeline text-generation · Library peft · Repo reimu996/OneReason-0.8B-Frontier-SFT-Epoch1

Note8 aoûthuggingface.co/reimu996/OneReason-0.8B-Frontier-SFT-Epoch1

Source context: 41 downloads · 0 likes · Pipeline text-generation · Library peft · Repo reimu996/OneReason-0.8B-Frontier-SFT-Epoch1