---
license: apache-2.0
base_model: ByteDance-Seed/Seed-Coder-8B-Instruct
library_name: peft
tags:
- lora
- unsloth
- seed-coder
- rust
- strandset
- code
---

# Seed-Coder-8B-Instruct Rust Strandset LoRA

LoRA adapter trained with Unsloth Studio on a 20k-row subset of `Fortytwo-Network/Strandset-Rust-v1`.

Base model:

`ByteDance-Seed/Seed-Coder-8B-Instruct`

Training data:

`Fortytwo-Network/Strandset-Rust-v1`

Mapping used:

- `input_data` → user
- `output_data` → assistant
- `task_category` → system
- `crate_name` → system
- `test` → none

Training config:

- Method: LoRA
- Context: 4096
- Epochs: 1
- LR: 2e-4
- Rank: 16
- Alpha: 32
- Dropout: 0.0
- Batch size: 16
- Grad accum: 2
- Effective batch: 32
- Weight decay: 0.001
- Warmup steps: 25
- Packing: off
- Train on completions: on

Note: this adapter was trained on Strandset-style structured Rust code tasks. It may emit JSON-style wrappers such as `{"code": "..."}` depending on prompting.