Commit History
-
Update model card for Qwen397B custom SFT adapter
Verified signatureConcise model-card summary for the promoted env-0 Qwen397B-data custom SFT LoRA adapter.b585e34 -
Backup Qwen3.5-397B-data custom SFT adapter qwen35-397b-data-qwen35-9b-custom-sft-20260630T042600Z (#4)
- Backup Qwen3.5-397B-data custom SFT adapter qwen35-397b-data-qwen35-9b-custom-sft-20260630T042600Z (92380a83764ec2d8b2103a3895e24e49a508d1d9)fa34e22
-
Update Fireworks 180-run evaluation report
Verified signatured0f7a66 -
Update model card with Fireworks full60 validation
Verified signature6561351
-
Add current env0 mobile model tag to model card
Verified signature294bcc0 -
Update model card for env0 mobile SFT adapter
Verified signature0bd9407 -
Update env0 mobile Qwen3.5-9B SFT adapter env0-mobile-pr828-qwen35-bf16-lora-8k-h100-20260625T084605Z (#1)
- Update env0 mobile Qwen3.5-9B SFT adapter env0-mobile-pr828-qwen35-bf16-lora-8k-h100-20260625T084605Z (818b38e7dfeb06da5446ad1e5719f22cafc3fbec)331eb2a
-
Document v0.0.1 LoRA training recipe and results
Verified signatureRecords completed seq2048 LoRA SFT data recipe, training parameters, held-in eval results, and release caveats. Excludes the in-progress QLoRA run.575a490 -
Update model card with general-agent training results
Verified signatureAdds completed seq2048 training parameters, held-in eval results, and current seq8192 QLoRA run status.87462fa -
Update README.md
Verified signature30c30ee -
Add model card metadata and SFT parameters
Verified signature678841c -
Update model card training parameters
Verified signatureab5bb0a -
Replace with general-agent Qwen3.5 step-200 LoRA adapter
Verified signatureClean replacement from benchflow/general-agent-qwen35-9b-sft-seq2048-fresh-20260624T131847Z-lora. Removed prior env0 task-lite adapter/results artifacts and uploaded the current general-agent Qwen3.5 step-200 LoRA adapter files.04f8298
-
Upload Qwen3.5 env-0 task-lite QLoRA adapter
Verified signature5b02f4d -
initial commit
Verified signature9046999