LFM2.5-2.6B ToolACE LoRA (n=n3000) — ONNX
Merged LoRA fine-tune of LiquidAI/LFM2.5-2.6B on
Team-ACE/ToolACE
(n3000 subset), exported for in-browser ORT Web.
Files
| Path | Notes |
|---|---|
onnx/model.onnx |
Graph (opset 18) |
onnx/model.onnx_data |
Consolidated FP32 weights |
| tokenizer / config | From base + FT |
IO
- inputs:
input_ids[batch, seq],attention_mask[batch, seq] - outputs:
logits[batch, seq, vocab] - Prefill-style (
use_cache=False). No KV-cache I/O.
Validation
FP32 ORT vs PyTorch max abs diff: 1.335e-04 (threshold 1e-3).
Train recipe
- LoRA r=16, attn+MLP (no lm_head)
- TRL SFTTrainer, completion_only_loss
- batch 1 × accum 16, seq 2048, 1 epoch
- Adapter path:
lfm25_toolace_r16_n3000
License
LFM 1.0 (inherited from base). ToolACE dataset license applies to fine-tune data.
- Downloads last month
- 187