Sponsored by YouArt
Toolify Toolify logo
AI Models
prereleasetrainingpackage

ApacheOne / prereleasetrainingpackage

Run on huggingface.co
huggingface.co
Total runs: 25
24-hour runs: -2
7-day runs: -30
30-day runs: -103
Model's Last Updated: July 24 2026
text-generation

Introduction of prereleasetrainingpackage

Model Details of prereleasetrainingpackage

Bonsai-27B packed-Q1 native LoRA training release

This is a reproducible engineering release for native LoRA training directly against the packed Q1_0 Bonsai-27B base model in a pinned Prism/Mintplex llama.cpp tree.

The repository contains adapters, deterministic checkpoints, dataset shards, source changes, clean-build evidence, verification scripts, reports and an optional Linux/CUDA build. The 3.8 GB base GGUF is not redistributed.

Release status
Stage Result
Step 8: native multi-target packed-Q1 LoRA PASS
Step 9: deterministic dataset pipeline PASS
Step 10: native training and exact checkpointing PASS
Step 11: correctness and quality acceptance PASS
Step 12: performance and stability acceptance PASS
Step 13: clean reproducibility build PASS
What is proven
  • Packed Q1_0 base weights remain immutable.
  • Six LoRA tensors are optimized without a persistent expanded base model.
  • Checkpoint save/reload is exact.
  • Interrupted accumulation resumes deterministically.
  • Independent resume branches produced byte-identical checkpoints, adapters and state fingerprints.
  • Load/unload, quick soak, RAM and VRAM checks passed.
  • The patch applies to commit 7529fdaaf99ffdc5ca71ace9c7409a56b27ad92f and selected targets build in a clean worktree.
LoRA targets
Base tensor Family Rank Alpha Base shape
blk.0.ssm_alpha.weight SSM 4 8 48 × 5120
blk.11.attn_k.weight attention 4 8 1024 × 5120
blk.0.ffn_down.weight FFN 4 8 5120 × 17408

Total trainable LoRA values: 135,360 .

Quality result

This was a tiny proof run, not a quality fine-tune.

  • Train mean-token NLL, full minus zero adapter: 0.00021834747786
  • Validation mean-token NLL, full minus zero adapter: 9.73401665583e-06
  • Validation improved: no

The adapter is numerically connected and stable, but the proof run is too small to establish a quality gain.

Performance snapshot
Measurement Result
Base end-to-end generation 3.692 tokens/s
Trained-adapter end-to-end generation 3.379 tokens/s
Base fresh-process load 0.817 GiB/s
Trained fresh-process load 0.748 GiB/s
Peak process RSS 3980.6 MiB
Peak observed GPU memory 9972.0 MiB
Load/unload cycles 3
Quick soak 192 requested tokens
Training microsteps/minute 0.843330
Training updates/minute 0.562220
Primary artifacts
Artifact Size SHA256
step10_adapter_final.gguf 529.50 KiB 6ba256d4e1836a177a8c7519d05a95639d47f4ee181fb6fcd438eee40805549f
multi_target_adapter_initial.gguf 529.50 KiB 84d835c964c4a0ae32fed9be2106124ff9319b74317ba9cdb0ea21069150edb5
checkpoint_latest.p10ck 2.07 MiB 1ba5545af5c33aacd7c1d2b395afe0e53e4fac5f1fd07ea56353c5a0c9fa64b9
quick_resume_adapter.gguf 529.50 KiB c6c163276a50c144315543a49ecdccd725608b5e3a653733a4a589369e0233d2
quick_resume_checkpoint.p10ck 2.07 MiB 7c8e9b000eac8fa3ca60883b76f6a6c2ffe6126d97b3c861dfef70dcc4e3080c
Base model identity
  • Repository: prism-ml/Bonsai-27B-gguf
  • Revision: 0469926cd8878dbddb5b883740ab3df060058696
  • Required file: Bonsai-27B-Q1_0.gguf
  • Bytes: 3803452480
  • SHA256: 17ef842e47450caeb8eaa3ebfbbab5d2f2278b62b79be107985fb69a2f819aa0 
python -m pip install -r reproduce/requirements.txt
python reproduce/download_models.py
python reproduce/restore_and_build.py
python reproduce/verify_release.py
Load the adapter 
./binaries/linux-colab-cuda/llama-completion   -m /path/to/Bonsai-27B-Q1_0.gguf   --lora adapters/step10_adapter_final.gguf   -p "User: Explain deterministic checkpoint resume.\nAssistant:"   -n 64 --temp 0 -ngl 999 -no-cnv
Limitations
  • This is a proof-of-training release, not a broadly trained production LoRA.
  • Validation NLL was slightly worse by 9.73401665583e-06 .
  • The Linux build is environment-specific.
  • The quick soak is not an hours-long production endurance test.
  • Upstream source and base-model licenses and terms apply.

Runs of ApacheOne prereleasetrainingpackage on huggingface.co

25
Total runs
-2
24-hour runs
-4
3-day runs
-30
7-day runs
-103
30-day runs

More Information About prereleasetrainingpackage huggingface.co Model

More prereleasetrainingpackage license Visit here:

https://choosealicense.com/licenses/other

prereleasetrainingpackage huggingface.co

prereleasetrainingpackage huggingface.co is an AI model on huggingface.co that provides prereleasetrainingpackage's model effect (), which can be used instantly with this ApacheOne prereleasetrainingpackage model. huggingface.co supports a free trial of the prereleasetrainingpackage model, and also provides paid use of the prereleasetrainingpackage. Support call prereleasetrainingpackage model through api, including Node.js, Python, http.

prereleasetrainingpackage huggingface.co Url

https://huggingface.co/ApacheOne/prereleasetrainingpackage

ApacheOne prereleasetrainingpackage online free

prereleasetrainingpackage huggingface.co is an online trial and call api platform, which integrates prereleasetrainingpackage's modeling effects, including api services, and provides a free online trial of prereleasetrainingpackage, you can try prereleasetrainingpackage online for free by clicking the link below.

ApacheOne prereleasetrainingpackage online free url in huggingface.co:

https://huggingface.co/ApacheOne/prereleasetrainingpackage

prereleasetrainingpackage install

prereleasetrainingpackage is an open source model from GitHub that offers a free installation service, and any user can find prereleasetrainingpackage on GitHub to install. At the same time, huggingface.co provides the effect of prereleasetrainingpackage install, users can directly use prereleasetrainingpackage installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

prereleasetrainingpackage install url in huggingface.co:

https://huggingface.co/ApacheOne/prereleasetrainingpackage

Url of prereleasetrainingpackage

prereleasetrainingpackage huggingface.co Url

Provider of prereleasetrainingpackage huggingface.co

ApacheOne
ORGANIZATIONS
huggingface.co

Other API from ApacheOne

 huggingface.co
ApacheOne/WAN_loRAs

Total runs: 25
Run Growth: 1
Growth Rate: 4.35%
Updated:March 28 2026
huggingface.co
ApacheOne/CKPTs

Total runs: 4
Run Growth: -4
Growth Rate: -100.00%
Updated:April 28 2025
huggingface.co
ApacheOne/E-Hunyuan

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated:August 18 2025
huggingface.co
ApacheOne/H3_loras

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated:August 20 2026
huggingface.co
ApacheOne/Daam2.0

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated:August 17 2025