Instructions to use laion/ablation-pymethods2test-shaped-45-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use laion/ablation-pymethods2test-shaped-45-8B with Transformers:

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

pipe = pipeline("text-generation", model="laion/ablation-pymethods2test-shaped-45-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("laion/ablation-pymethods2test-shaped-45-8B")
model = AutoModelForCausalLM.from_pretrained("laion/ablation-pymethods2test-shaped-45-8B")
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 laion/ablation-pymethods2test-shaped-45-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "laion/ablation-pymethods2test-shaped-45-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "laion/ablation-pymethods2test-shaped-45-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/laion/ablation-pymethods2test-shaped-45-8B

SGLang

How to use laion/ablation-pymethods2test-shaped-45-8B 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 "laion/ablation-pymethods2test-shaped-45-8B" \
    --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": "laion/ablation-pymethods2test-shaped-45-8B",
		"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 "laion/ablation-pymethods2test-shaped-45-8B" \
        --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": "laion/ablation-pymethods2test-shaped-45-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use laion/ablation-pymethods2test-shaped-45-8B with Docker Model Runner:
```
docker model run hf.co/laion/ablation-pymethods2test-shaped-45-8B
```

ablation-pymethods2test-shaped-45-8B / README.md

penfever

Upload README.md with huggingface_hub

a8c25c6 verified about 1 month ago

preview code

Raw

History Blame Contribute Delete

1.62 kB

	---
	base_model: laion/GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink
	tags:
	- rl
	- skyrl
	- agentic
	- swe
	library_name: transformers
	---

	# ablation-pymethods2test-shaped-45-8B

	RL (SkyRL GRPO) checkpoint from the shaped-reward ablation of the a3-successor
	study. Reward = shaped pass-ratio (fraction of tests passing, `reward_shaper=pass_ratio`),
	as opposed to the binary all-tests-pass reward of the a3 series.

	- Base model: [laion/GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink](https://huggingface.co/laion/GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink) (a Qwen3-8B SFT)
	- Training dataset: [DCAgent/exp_rpt_pymethods2test-large](https://huggingface.co/datasets/DCAgent/exp_rpt_pymethods2test-large)
	- Checkpoint: `global_step_45`, selected as the best checkpoint by **EMA
	(alpha=1/3, trailing-5 window) of `reward/avg_raw_reward`** computed across
	the full 80-step training chain (EMA = 0.4712 at step 45).
	- Training: 80 steps total, `hf_save_interval=5`, 14x GH200 nodes on JSC Jupiter.

	The `rl_config.json` in this repo is the exact launch config used for reproducibility.

	## Training Traces

	Training-time Daytona/Harbor rollouts for this run are uploaded as
	a companion dataset:
	[penfever/ablation-pymethods2test-shaped](https://huggingface.co/datasets/penfever/ablation-pymethods2test-shaped)

	The dataset contains the `last` episode of each trial (per
	`make_and_upload_trace_dataset --episodes last`) — the same rollouts
	the policy was trained on after rollback / truncation.