---
license: other
license_name: lfm1.0
base_model: LiquidAI/LFM2.5-2.6B
library_name: transformers.js
pipeline_tag: text-generation
tags:
- onnx
- lora
- toolace
- lfm2.5
- peft
- webgpu
---

# LFM2.5-2.6B ToolACE LoRA (n=n3000) — ONNX

Merged LoRA fine-tune of [`LiquidAI/LFM2.5-2.6B`](https://huggingface.co/LiquidAI/LFM2.5-2.6B) on
[Team-ACE/ToolACE](https://huggingface.co/datasets/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.