Alpamys
|
cbc0a0e558
|
v0.16.0: embedding models, ONNX/TensorRT export, speculative decoding
New features:
- task: embedding — fine-tune sentence embedding models (BGE, E5, GTE)
with contrastive, triplet, or cosine loss and configurable pooling
- soup export --format onnx — ONNX export via optimum
- soup export --format tensorrt — TensorRT-LLM export for GPU inference
- soup serve --speculative-decoding — draft model for 2-3x faster generation
(transformers assisted generation + vLLM native speculative decoding)
- soup init --template embedding — new template for embedding fine-tuning
Security:
- ONNX export: removed unconditional trust_remote_code, added warning
- Speculative decoding: SSRF protection (URL blocked), warning panel
- vLLM speculative: URL validation rejects http:// schemes
- TensorRT export: separated try/except per subprocess call
- Embedding config: Literal constraints, margin gt=0 validation
1270 tests, 52 test files, 58% coverage
|
2026-03-26 12:41:39 +05:00 |
|
Alpamys
|
f03b578428
|
Phase 2.5: add export GGUF, merge LoRA, resume training, W&B integration (v0.2.0)
New commands:
- soup export --model ./output --format gguf --quant q4_k_m
- soup merge --adapter ./output
New train flags:
- soup train --resume auto (or --resume ./checkpoint-500)
- soup train --wandb
184 tests passing (was 147), all lint clean.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
|
2026-03-03 22:29:44 +05:00 |