Instructions to use imdatta0/qwen3-4b-swegym-moto-kl02-multihint-grpo-b02-lr2e6-s25-adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use imdatta0/qwen3-4b-swegym-moto-kl02-multihint-grpo-b02-lr2e6-s25-adapter with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("/mnt/disks/unslothai/datta0/.cache/hub/models--unsloth--Qwen3-4B-Instruct-2507/snapshots/992063681dc2f7de4ee976110199552935cad284")
model = PeftModel.from_pretrained(base_model, "imdatta0/qwen3-4b-swegym-moto-kl02-multihint-grpo-b02-lr2e6-s25-adapter")

Transformers

How to use imdatta0/qwen3-4b-swegym-moto-kl02-multihint-grpo-b02-lr2e6-s25-adapter with Transformers:

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

pipe = pipeline("text-generation", model="imdatta0/qwen3-4b-swegym-moto-kl02-multihint-grpo-b02-lr2e6-s25-adapter")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("imdatta0/qwen3-4b-swegym-moto-kl02-multihint-grpo-b02-lr2e6-s25-adapter", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use imdatta0/qwen3-4b-swegym-moto-kl02-multihint-grpo-b02-lr2e6-s25-adapter with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "imdatta0/qwen3-4b-swegym-moto-kl02-multihint-grpo-b02-lr2e6-s25-adapter"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "imdatta0/qwen3-4b-swegym-moto-kl02-multihint-grpo-b02-lr2e6-s25-adapter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/imdatta0/qwen3-4b-swegym-moto-kl02-multihint-grpo-b02-lr2e6-s25-adapter

SGLang

How to use imdatta0/qwen3-4b-swegym-moto-kl02-multihint-grpo-b02-lr2e6-s25-adapter 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 "imdatta0/qwen3-4b-swegym-moto-kl02-multihint-grpo-b02-lr2e6-s25-adapter" \
    --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": "imdatta0/qwen3-4b-swegym-moto-kl02-multihint-grpo-b02-lr2e6-s25-adapter",
		"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 "imdatta0/qwen3-4b-swegym-moto-kl02-multihint-grpo-b02-lr2e6-s25-adapter" \
        --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": "imdatta0/qwen3-4b-swegym-moto-kl02-multihint-grpo-b02-lr2e6-s25-adapter",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use imdatta0/qwen3-4b-swegym-moto-kl02-multihint-grpo-b02-lr2e6-s25-adapter with Docker Model Runner:
```
docker model run hf.co/imdatta0/qwen3-4b-swegym-moto-kl02-multihint-grpo-b02-lr2e6-s25-adapter
```

Qwen3-4B SWE-Gym Moto KL02 Multi-Hint GRPO Step-25 Adapter

This is a PEFT LoRA adapter for unsloth/Qwen3-4B-Instruct-2507, trained for agentic code repair on the local SWE-Gym moto held-out investigation using a search/replace patch format and honest anchored retrieval.

This checkpoint is a short GRPO continuation from the stronger KL02 adapter with the structural multi-file prompt hint enabled during training. It is an ablation artifact, not the best Qwen3-4B checkpoint from the investigation.

Local source checkpoint:

/mnt/disks/unslothai/datta0/cache/qwen3-grpo-patch/20260605_005347_swegym_q4b-kl02-multihint-grpo-b02-lr2e6-s25_c1a36f8/checkpoints/checkpoint-25

Training

Base model: unsloth/Qwen3-4B-Instruct-2507
Initial adapter: imdatta0/qwen3-4b-swegym-moto-kl02-adapter
Prompt mode: structural multi-file search/replace hint enabled
Objective: GRPO
Beta: 0.02
Learning rate: 2e-6
Steps: 25
Eval split: local SWE-Gym moto held-out, 35 tasks

Held-Out Result

run	greedy	mean reward	patch applied
KL02 + prompt hint, step 0 baseline	9/35	0.4563	0.8571
GRPO continuation, step 25	8/35	0.4234	0.8286

The continuation was stable but negative on the held-out greedy metric. It regressed from the inherited step-0 baseline, so no pass@8 evaluation was promoted for this checkpoint.

The stronger artifact for normal use is:

imdatta0/qwen3-4b-swegym-moto-kl02-adapter

Use that adapter with the structural multi-file prompt hint at runtime for the best measured deterministic behavior from this branch.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base = "unsloth/Qwen3-4B-Instruct-2507"
adapter = "imdatta0/qwen3-4b-swegym-moto-kl02-multihint-grpo-b02-lr2e6-s25-adapter"

tokenizer = AutoTokenizer.from_pretrained(adapter)
model = AutoModelForCausalLM.from_pretrained(base)
model = PeftModel.from_pretrained(model, adapter)

Limitations

This adapter requires the base model and is not a merged full model.
This is a research checkpoint for SWE-Gym style code repair, not a general coding assistant release.
It was evaluated only on the local SWE-Gym moto held-out split used in this investigation.
The step-25 continuation is not a frontier checkpoint; it regressed relative to the inherited KL02 prompt-hint baseline.
Metrics depend on the repository's retrieval, prompt, search/replace extraction, patch application, and sandbox scoring code.

Downloads last month: 6

Model tree for imdatta0/qwen3-4b-swegym-moto-kl02-multihint-grpo-b02-lr2e6-s25-adapter

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

unsloth/Qwen3-4B-Instruct-2507

Adapter

(443)

this model