Instructions to use Schiltmans/Ternary-Bonsai-2-27B-DFlash2-ft5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Schiltmans/Ternary-Bonsai-2-27B-DFlash2-ft5 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download Schiltmans/Ternary-Bonsai-2-27B-DFlash2-ft5 --local-dir Ternary-Bonsai-2-27B-DFlash2-ft5
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Commit History
9 days ago
-
Card: the fork release supports DFlash 2; GGUF in three quantizations
Verified signature315d40e
20 days ago
-
Card: a shorter card, the same figures
Verified signature696b587
21 days ago
-
Card: protocol decode results against stock and ProCreations
Verified signature4582bbb -
docs: add r3 throughput on mlx-dspark
Verified signatured85cbc9 -
docs: add the GGUF and second-runtime throughput
Verified signature9ebcf49 -
docs: add the Mac stack comparison and oMLX status
Verified signaturedc3e552 -
docs: add the ProCreations comparison and a derivative result
Verified signaturef780fc3 -
docs: link the evidence bundle and eval prompts
Verified signature917c05d -
Correct the r3 comparison's status and remove relative dates
Verified signaturef5b1334 -
Update the model card: second runtime, fork result, 4-bit variant
Verified signaturedf485e2
22 days ago
-
Remove a stray upload status file
Verified signature2a2c2c1 -
Add the ft5 drafter weights, licence and model card
Verified signature83a6eb4 -
initial commit
Verified signaturec8047c5