--- title: LLaDA2.2-flash canonical_url: "https://www.modelscope.ai/models/inclusionAI/LLaDA2.2-flash" md_url: "https://www.modelscope.ai/models/inclusionAI/LLaDA2.2-flash.md" repository: inclusionAI/LLaDA2.2-flash last_updated: 2026-08-21 license: apache-2.0 model_type: - llada2_moe architectures: - LLaDA2MoeModelLM parameters: 102.9B tensor_type: - BF16 - F32 library_name: - pytorch - transformer - safetensors frameworks: - pytorch downloads: 137 stars: 0 tags: - dllm - diffusion - llm - text_generation --- # LLaDA2.2-flash > LLaDA2.2-flash - An open-source model by inclusionAI on ModelScope. LLaDA2.2-flash is an agent-oriented diffusion language model in the LLaDA2 series. By introducing Levenshtein Editing (with DELETE and INSERT control tokens) to diffusion language modeling,… inclusionAI/LLaDA2.2-flash is a 102.9B-parameter machine learning model on ModelScope. licensed under apache-2.0. - **Repository**: inclusionAI/LLaDA2.2-flash - **License**: apache-2.0 - **Parameters**: 102.9B - **Tags**: dllm, diffusion, llm, text_generation - **Downloads**: 137 - **Stars**: 0 - **Last updated**: 2026-08-21 Source: https://www.modelscope.ai/models/inclusionAI/LLaDA2.2-flash --- # LLaDA2.2-flash **LLaDA2.2-flash** is an agent-oriented diffusion language model in the LLaDA2 series. By introducing **Levenshtein Editing** (with `DELETE` and `INSERT` control tokens) to diffusion language modeling, it represents the LLaDA2 series' first step in agentic applications, including long-context tool use, multi-turn interaction, and robust error correction.For more information, please refer to our [technical report](https://github.com/inclusionAI/LLaDA2.X/blob/main/LLaDA2_2_tech_report.pdf).
--- ## 📊 Benchmarks The following tables compare **LLaDA2.2-flash** and **Ling-2.6-flash** in terms of agentic benchmark scores and throughput (TPS). **Agentic benchmark scores** | Benchmark | LLaDA2.2-flash | Ling-2.6-flash | | --- | ---: | ---: | | SWE-bench Verified | 49.28 | 61.20† | | SWE-bench Pro | 30.10 | 31.88 | | SWE-bench Multilingual | 25.00 | 33.73 | | τ²-Bench | 80.33 | 76.36† | | Claw-Eval | 64.22 | 64.56† | | PinchBench | 81.66 | 81.30† | | MCP-Atlas | 46.21 | 41.12 | | BFCL-V4 | 60.78 | 66.81 | > **LLaDA2.2-flash evaluation setup:** The SWE-bench series was evaluated using the Claude Code scaffold. Across all benchmarks, we used a 128K context window with `temperature=1.0`, `block_length=32`, `threshold=0.5`, and `editing_threshold=0.0`. Each score represents the average of five runs. † The Ling-2.6-flash score on SWE-bench Verified is taken from the Ling and Ring 2.6 Technical Report, where it was obtained using the OpenHands scaffold. The Ling-2.6-flash scores on τ²-Bench, Claw-Eval, and PinchBench are also sourced from the technical report, whereas its SWE-bench Pro and SWE-bench Multilingual scores were evaluated by us using the same Claude Code scaffold as LLaDA2.2-flash. **Throughput (TPS)** | Benchmark | LLaDA2.2-flash (TPS) | Ling-2.6-flash (TPS) | | --- | ---: | ---: | | SWE-bench Verified | 519.0 | 303.2 | | SWE-bench Pro | 485.3 | 283.4 | | SWE-bench Multilingual | 459.5 | 200.6 | | τ²-Bench | 592.8 | 334.9 | | BFCL-V4 | 703.82 | 331.5 | > **Ling-2.6-flash evaluation setup:** MTP was enabled with 4 draft tokens. More results will be released in the upcoming technical report. --- ## 🚀 Highlights + **Efficient 128K Diffusion Infrastructure**: LLaDA2.2-flash extends the context window to **128K** and introduces **Block Routing**, which bounds MoE expert activation at the diffusion-block level to enable efficient long-context agentic workloads. + **Levenshtein Editing**: We introduces **DELETE** and **INSERT** control tokens, allowing diffusion decoding to edit sequence structure, remove redundant content, and create insertion slots during parallel generation. + **Agentic Reinforcement Learning**: We propose **Levenshtein Editing ELBO-based Block-level Policy Optimization (L-EBPO)**, which leverages agentic environmental rewards to train levenshtein editing and error correction in multi-turn tool-use scenarios. --- ## 📦 Model Variants | Model ID | Description | Hugging Face Link | | --- | --- | --- | | `inclusionAI/LLaDA2.2-flash` | Agent-oriented MoE diffusion language model with Levenshtein Editing. | [🤗 Model Card](https://huggingface.co/inclusionAI/LLaDA2.2-flash) | --- ## 🔍 Model Overview **LLaDA2.2-flash** has the following specifications: + **Type**: Mixture-of-Experts (MoE) Diffusion Language Model with Levenshtein Editing + **Context Length**: 128K tokens + **Levenshtein Editing Control Tokens**: `DELETE`, `INSERT` + **Total Parameters (Non-Embedding)**: 100B + **Number of Layers**: 32 + **Attention Heads**: 32 + **Positional Encoding**: Rotary Position Embedding (RoPE) + **Vocabulary Size**: 157,184 --- ## 🤗 Hugging Face Transformers Make sure you have `transformers` and its dependencies installed. ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer model_path = "inclusionAI/LLaDA2.2-flash" device = "auto" model = AutoModelForCausalLM.from_pretrained( model_path, trust_remote_code=True, device_map=device, ) model = model.to(torch.bfloat16) model.eval() tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True) prompt = """Calculate 1+5-28*0.5-200=?""" input_ids = tokenizer.apply_chat_template( [{"role": "user", "content": prompt}], add_generation_prompt=True, tokenize=True, return_tensors="pt", ).input_ids generated_tokens = model.generate( inputs=input_ids, eos_early_stop=True, gen_length=512, block_length=32, threshold=0.5, editing_threshold=0.0, temperature=0.0, ) generated_answer = tokenizer.decode( generated_tokens[0], skip_special_tokens=True, ) print(generated_answer) ``` ### Best Practices To achieve optimal performance, we recommend starting with the following settings: 1. **Sampling Parameters**: Use `block_length=32`, `temperature=0.0`, `top_p=None`, and `top_k=None` as stable default settings. 2. **Denoising Thresholds**: Tune `threshold`, `editing_threshold`, and `max_post_steps` according to the speed-quality trade-off required by the application. Lower thresholds may improve inference speed but can lead to increased repetition or unstable outputs. 3. **Long-Context Agentic Workloads**: For long-context tool-use and multi-turn agent applications, we recommend using **SGLang** as the serving backend. Please ensure that the serving stack is configured for the 128K context window and the model's MoE diffusion inference requirements. --- ## 🤖 ModelScope If you are in mainland China, we strongly recommend accessing our model from 🤖 [ModelScope](https://modelscope.cn/models/inclusionAI/LLaDA2.2-flash) --- ## Deployment ### SGLang SGLang deployment support is coming soon. --- ## 🌐 License This project is licensed under the terms of the [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0). --- ## 🤝 Contact & Collaboration For questions, collaboration opportunities, or feedback, please reach out via [Hugging Face](https://huggingface.co/inclusionAI/LLaDA2.2-flash) or open an issue in the [repository](https://github.com/inclusionAI). Join us in advancing open, efficient, and intelligent diffusion language models for agentic applications. ---