Instructions to use ubicloud/SWE-Eff-Hard-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ubicloud/SWE-Eff-Hard-14B with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("/workspace/Ubi/model/Qwen3-14B")
model = PeftModel.from_pretrained(base_model, "ubicloud/SWE-Eff-Hard-14B")

Transformers

How to use ubicloud/SWE-Eff-Hard-14B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ubicloud/SWE-Eff-Hard-14B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ubicloud/SWE-Eff-Hard-14B")
model = AutoModelForCausalLM.from_pretrained("ubicloud/SWE-Eff-Hard-14B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ubicloud/SWE-Eff-Hard-14B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ubicloud/SWE-Eff-Hard-14B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ubicloud/SWE-Eff-Hard-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ubicloud/SWE-Eff-Hard-14B

SGLang

How to use ubicloud/SWE-Eff-Hard-14B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ubicloud/SWE-Eff-Hard-14B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ubicloud/SWE-Eff-Hard-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ubicloud/SWE-Eff-Hard-14B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ubicloud/SWE-Eff-Hard-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ubicloud/SWE-Eff-Hard-14B with Docker Model Runner:
```
docker model run hf.co/ubicloud/SWE-Eff-Hard-14B
```

Model Summary

SWE-Eff†-14B is a LoRA fine-tuned SWE agent model based on Qwen3-14B, trained on ~3K high-quality filtered trajectories from R2EGym with a 32K context window. It uses suggestive thinking with masked supervision (mask_think) to inject reasoning prompts into training while masking them from loss, preserving the model's autonomous reasoning while implicitly guiding efficient agent behaviors.

SWE-Eff† serves as the conservative complementary model — optimized for harder problems involving multi-file logic, unclear root causes, and complex API interactions. For structured tasks with clear error traces, see the default model SWE-Eff.

Suggestive Thinking

Unlike the default SWE-Eff model, SWE-Eff† injects reasoning prompts (wrapped in <think...</think blocks) into each assistant message during training to encourage deeper reasoning:

Let's think step by step ... (encourages deeper reasoning before actions)
Let's view, think, edit, test ... (standardizes workflows)
If I get stuck in a loop, I need to think of different solutions to break out of it. (mitigates repetitive action loops)

The mask_think mechanism excludes the content inside thinking blocks from loss computation while retaining supervision on the <think and </think tokens. This allows suggestive guidance to influence the model implicitly while preserving autonomous reasoning behavior.

Training Data

Fine-tuned on filtered-R2EGym-SFT-Trajectories — 3,218 high-quality trajectories filtered from R2EGym-SFT via a multi-stage pipeline:

Basic Quality: exit_status = Submitted & resolved = True
Behavioral Soundness: Redundant loop detection & excessive search ratio filtering
Hallucination Control: Shortcut pattern & false reasoning detection
Thought–Action Alignment: Intent vs. action consistency enforcement

Training Configuration

Item	Value
Base Model	Qwen3-14B
Precision	bfloat16
PEFT Method	LoRA
LoRA Rank (r)	16
LoRA Alpha	32
LoRA Dropout	0.2
Target Modules	q/k/v/o/up/down/gate_proj
Adapter Size	246 MB
Global Batch Size	16
Gradient Accumulation	8
Learning Rate	2e-4
LR Scheduler	Cosine
Warmup Ratio	0.05
Weight Decay	0.1
Training Epochs	3
Total Training Time	~10.5 h
Hardware	2 × H200
Maximum Context Length	32,768 tokens
Key Modification	Suggestive thinking + `mask_think`

Evaluation

Evaluated on SWE-bench Verified using R2E-Gym scaffold with 32K context, 100-turn limit, temperature=0.6, top_p=0.95, and function calling disabled.

Metric	SWE-Eff (Default)	SWE-Eff† (Complementary)	SWE-Eff‡ (Union)
Resolved rate	21.6%	20.6%	30.4%
Avg steps	37.1	44.5 (+20%)	—
Submission success rate	43.2%	55.3%	—
Edit success rate	54.2%	63.2%	—
>80-step resolve rate	2.0% (1/51)	13.7% (7/51)	—

Usage

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-Eff-Hard-14B")

When to Use

SWE-Eff† (this model): Multi-file logic, unclear root causes, complex API interactions, known hard projects (e.g., sympy, sphinx, psf)
SWE-Eff: Bugs with clear error traces, localized to a single file, structured repositories (e.g., django, scikit-learn, xarray)

Downloads last month: 18

Model tree for ubicloud/SWE-Eff-Hard-14B

Base model

Qwen/Qwen3-14B-Base

Finetuned

Qwen/Qwen3-14B

Adapter

(323)

this model