Instructions to use wckwan/Alfworld-Olmo3-7B-Adaptive-Pivot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wckwan/Alfworld-Olmo3-7B-Adaptive-Pivot with Transformers:

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

pipe = pipeline("text-generation", model="wckwan/Alfworld-Olmo3-7B-Adaptive-Pivot")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("wckwan/Alfworld-Olmo3-7B-Adaptive-Pivot", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use wckwan/Alfworld-Olmo3-7B-Adaptive-Pivot with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wckwan/Alfworld-Olmo3-7B-Adaptive-Pivot"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wckwan/Alfworld-Olmo3-7B-Adaptive-Pivot",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/wckwan/Alfworld-Olmo3-7B-Adaptive-Pivot

SGLang

How to use wckwan/Alfworld-Olmo3-7B-Adaptive-Pivot 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 "wckwan/Alfworld-Olmo3-7B-Adaptive-Pivot" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wckwan/Alfworld-Olmo3-7B-Adaptive-Pivot",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "wckwan/Alfworld-Olmo3-7B-Adaptive-Pivot" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wckwan/Alfworld-Olmo3-7B-Adaptive-Pivot",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use wckwan/Alfworld-Olmo3-7B-Adaptive-Pivot with Docker Model Runner:
```
docker model run hf.co/wckwan/Alfworld-Olmo3-7B-Adaptive-Pivot
```

Alfworld-Olmo3-7B-Adaptive-Pivot

A allenai/Olmo-3-7B-Instruct policy trained as a multi-turn search agent (Search-R1 style) with Process-GRPO: a process reward model (Olmo-3-7B-Think verifier) scores each turn, with per-(group, turn-position) advantage normalization and verifier prompts that include the retrieved tool responses and the gold answer.

The model at the repository root is the final policy (training step 60). Intermediate checkpoints are provided under step_<STEP>/ subfolders.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

# Final model (repo root)
model = AutoModelForCausalLM.from_pretrained("wckwan/Alfworld-Olmo3-7B-Adaptive-Pivot")
tokenizer = AutoTokenizer.from_pretrained("wckwan/Alfworld-Olmo3-7B-Adaptive-Pivot")

# An intermediate checkpoint
model_step = AutoModelForCausalLM.from_pretrained("wckwan/Alfworld-Olmo3-7B-Adaptive-Pivot", subfolder="step_20")

Checkpoints

Root: final policy at step 60.

step_20/ — intermediate checkpoint at training step 20
step_40/ — intermediate checkpoint at training step 40

Training summary (step 60)

Process-reward score mean ≈ 0.93
Searches per trajectory ≈ 2.6 (non-collapsed, diverse multi-search policy)
Training-batch accuracy ≈ 0.49

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for wckwan/Alfworld-Olmo3-7B-Adaptive-Pivot

Base model

allenai/Olmo-3-1025-7B

Finetuned

allenai/Olmo-3-7B-Instruct-SFT

Finetuned

allenai/Olmo-3-7B-Instruct-DPO

Finetuned

allenai/Olmo-3-7B-Instruct

Finetuned

(310)

this model