Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more
Container

Run this model inference with full control and performance in your environment.

Learn more

Get help setting up a custom Dedicated Endpoints.

Talk with our engineer to get a quote for reserved GPU instances with discounts.

README

Model Summary

SWE-Qwen3-14B is a LoRA fine-tuned SWE agent model based on Qwen3-14B, trained on 20K filtered trajectories from SWE-Star collected under a modified OpenHands scaffold.

🔗 Data: SWE-Openhands-Devstral-32k-20K

Training Configuration

ItemValue
Base ModelQwen3-14B
PEFTLoRA (rank=32, alpha=64, dropout=0.1)
Target ModulesAll linear layers (q/k/v/o/up/down/gate_proj)
Training Data20K filtered SWE-Star trajectories
Max Context32,768 tokens
Epochs2 (1,250 steps)
Batch Size16 (micro=1/GPU, grad_accum=8)
Learning Rate1e-4, cosine, warmup 5%
History Truncationkeep_fraction=0.5
Hardware2× GPU (FSDP2)

Context length and history truncation. We use a maximum context length of 32,768 tokens. Since many agent trajectories exceed this limit, we enable history truncation with a keep fraction of 0.5: when a trajectory exceeds the window, the oldest turns are dropped while preserving the most recent 50%. This ensures the model always sees the most relevant context (recent edits, test results, error messages) rather than losing the tail end, which typically contains the final fix and submission.

Usage

python

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-14B", torch_dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-14B")
model = PeftModel.from_pretrained(base_model, "ubicloud/SWE-Qwen3-14B")

Model provider

ubicloud

Model tree

Base

Qwen/Qwen3-14B

Adapter

this model

Modalities

Input

Text

Output

Text

Pricing

Dedicated Endpoints

View details

Supported Functionality

Model APIs

Dedicated Endpoints

Container

More information

Explore FriendliAI today