Hugging Face's logo

banhchungtuongot
/
lfm-serving-w4-artifacts

Safetensors
Model card Files
xet
 Community

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

LFM serving artifacts and results

Uploaded: 2026-07-21T04:38:33.828663+00:00

Results

  • results/ from /workspace/lfm-serving/results, size 96.9MB

Checkpoint artifacts

  • lfm2-w4a16-gptq-g64-mlp10-15-bf16/ from /workspace/lfm-serving/artifacts/lfm2-w4a16-gptq-g64-mlp10-15-bf16, size 1.4GB
  • lfm2-w4a16-gptq-g64-attention-only/ from /dev/shm/artifacts-work/lfm2-w4a16-gptq-g64-attention-only, size 2.1GB
  • lfm2-w4a16-gptq-g64-mlp10-15-attn10-12-14-bf16/ from /dev/shm/artifacts-work/lfm2-w4a16-gptq-g64-mlp10-15-attn10-12-14-bf16, size 1.5GB
  • lfm2-w4a16-gptq-g128/ from /dev/shm/artifacts-stash/lfm2-w4a16-gptq-g128, size 770.2MB
  • lfm2-w4a16-gptq-g128-no-conv/ from /dev/shm/artifacts-stash/lfm2-w4a16-gptq-g128-no-conv, size 1007.7MB
  • lfm2-w4a16-gptq-g64-late-mlp-bf16/ from /dev/shm/artifacts-stash/lfm2-w4a16-gptq-g64-late-mlp-bf16, size 1.3GB
  • lfm2-w4a16-gptq-g64-mlp8-15-bf16/ from /dev/shm/artifacts-stash/lfm2-w4a16-gptq-g64-mlp8-15-bf16, size 1.5GB
  • lfm2-w4a16-gptq-g64-no-conv/ from /dev/shm/artifacts-stash/lfm2-w4a16-gptq-g64-no-conv, size 1020.7MB

Notes

  • Repos are private by default.
  • W4 artifacts are compressed-tensors/GPTQ experiments; see repository docs for pass/fail status.
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support