---
license: apache-2.0
base_model:
- allenai/MolmoWeb-4B
language:
- en
pipeline_tag: image-text-to-text
library_name: transformers
tags:
- multimodal
- molmo
- molmo2
- web-agent
- full-precision
- vllm-compatible
---

# ravilution/MolmoWeb-4B

This is a **full-precision** Hugging Face– and **vLLM-compatible** release of [`allenai/MolmoWeb-4B`](https://huggingface.co/allenai/MolmoWeb-4B), a vision-based web agent model by Ai2 capable of navigating and interacting with web browsers.

It follows the same idea as [`ravilution/MolmoWeb-8B-8bit-mlx`](https://huggingface.co/ravilution/MolmoWeb-8B-8bit-mlx): a personal Hub copy with a clear description and practical loading notes—here for the **4B** dense checkpoint rather than an MLX quantization.

> **Note:** This is a **4B** parameter model (four `safetensors` shards). A few **post-download patches** were applied locally so tokenization and generation metadata match what downstream stacks (including vLLM) expect: `eos_token_id` / `bos_token_id` / `pad_token_id`, `transformers_version` in `config.json` and `generation_config.json`, and the tokenizer pretokenizer regex (Mistral-style `(?i:...)` fix). Patches are **idempotent** if you re-run them on a fresh download.

Refer to the [original model card](https://huggingface.co/allenai/MolmoWeb-4B) for benchmarks, architecture, training data, and intended use.

## Use with Transformers

```bash
pip install -U transformers accelerate torch pillow
```

```python
from transformers import AutoProcessor, AutoModelForImageTextToText
import torch

model_id = "ravilution/MolmoWeb-4B"

model = AutoModelForImageTextToText.from_pretrained(
    model_id,
    trust_remote_code=True,
    torch_dtype=torch.float32,
    attn_implementation="sdpa",
    device_map="auto",
)
processor = AutoProcessor.from_pretrained(
    model_id,
    trust_remote_code=True,
    padding_side="left",
)
```

## Provenance

- **Upstream weights:** `allenai/MolmoWeb-4B`
- **Changes on top:** compatibility patches only (config / generation_config / tokenizer metadata as above); **no** retraining or architectural edits.

## License

Apache 2.0 — see the [original model](https://huggingface.co/allenai/MolmoWeb-4B) for details. Please review Ai2’s Responsible Use Guidelines for intended use.