Instructions to use ishaanranjan/slm-agent-action-router-qwen2-5-0-5b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ishaanranjan/slm-agent-action-router-qwen2-5-0-5b with Transformers:

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

pipe = pipeline("text-generation", model="ishaanranjan/slm-agent-action-router-qwen2-5-0-5b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("ishaanranjan/slm-agent-action-router-qwen2-5-0-5b")
model = AutoModelForMultimodalLM.from_pretrained("ishaanranjan/slm-agent-action-router-qwen2-5-0-5b")
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 ishaanranjan/slm-agent-action-router-qwen2-5-0-5b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ishaanranjan/slm-agent-action-router-qwen2-5-0-5b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ishaanranjan/slm-agent-action-router-qwen2-5-0-5b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ishaanranjan/slm-agent-action-router-qwen2-5-0-5b

SGLang

How to use ishaanranjan/slm-agent-action-router-qwen2-5-0-5b 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 "ishaanranjan/slm-agent-action-router-qwen2-5-0-5b" \
    --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": "ishaanranjan/slm-agent-action-router-qwen2-5-0-5b",
		"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 "ishaanranjan/slm-agent-action-router-qwen2-5-0-5b" \
        --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": "ishaanranjan/slm-agent-action-router-qwen2-5-0-5b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ishaanranjan/slm-agent-action-router-qwen2-5-0-5b with Docker Model Runner:
```
docker model run hf.co/ishaanranjan/slm-agent-action-router-qwen2-5-0-5b
```

Agent Action Router (Qwen2.5 0.5B)

This is a full-parameter supervised fine-tune of Qwen/Qwen2.5-0.5B-Instruct for one narrow, schema-bound developer-agent subroutine:

Choose the next harness action from a noisy progress report.

The model is one cell from the Parameter Floors for Developer-Agent Subroutines experiment. Labels are generated by deterministic oracles over real Python repositories; no teacher model or human judge labels the data.

Intended Use

Use this checkpoint inside the repository's verified subroutine harness, which renders the task-specific prompt, parses strict JSON, permits one localized schema-feedback retry, applies deterministic guards, and falls back to rules where appropriate. This is not a general coding assistant or chat model.

Evaluation

Evaluation uses up to 250 examples from HTTPX and Jinja2, both held out entirely from training. Decoding is greedy.

Metric	Result
Success after one schema retry	96.0%
First-pass success	96.0%
First-pass schema validity	100.0%
Base instruct success after retry	27.6% for the base instruct model
Rules-only success	27.7%

Experiment verdict for this subroutine: works at 494M.

Training

Training examples: 2000
Epochs: 3.0
Learning rate: 2e-05
Effective batch configuration: 16 per device x 2 gradient accumulation
Maximum sequence length: 2048
Seed: 0
Final training loss: 0.177046
Reproduction hardware: one NVIDIA A100 80GB PCIe
Source revision: d0fd7bf

The dataset was generated from pinned Flask, Click, and Rich repositories for training/validation. HTTPX and Jinja2 were reserved for testing.

Limitations

The checkpoint is specialized to one closed JSON schema and should not be expected to retain broad instruction-following ability. The experiment mixes two base-model families across its size sweep. Some subroutines are better served by deterministic rules; consult the verdict above before deployment.

License

Apache-2.0, following the base model. Experiment code is MIT licensed.

Downloads last month: -

Safetensors

Model size

0.5B params

Tensor type

F32

Model tree for ishaanranjan/slm-agent-action-router-qwen2-5-0-5b

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-0.5B-Instruct

Finetuned

(839)

this model

Collection including ishaanranjan/slm-agent-action-router-qwen2-5-0-5b

Parameter Floors for Developer-Agent Subroutines

Collection

Full-parameter SFT checkpoints for eight deterministic, schema-verified coding-agent subroutines across 135M to 1.5B. • 32 items • Updated 1 day ago

Evaluation results

Success after one schema-feedback retry on Held-out HTTPX and Jinja2 oracle benchmark
self-reported

0.960
First-pass schema validity on Held-out HTTPX and Jinja2 oracle benchmark
self-reported

1.000