--- license: apache-2.0 tags: - finetuned - chat language: - en - ko - ja pipeline_tag: text-generation library_name: transformers extra_gated_fields: Full Name: text Email: text Organization: text --- # Trida-7B-Preview ## Introduction 🚀 Trida-7B-Preview: Block Diffusion Language Model We introduce Trida-7B-Preview, a high-performance 7-billion parameter language model representing the first publicly released Block Diffusion Language Model to originate from Korea. ### Model Overview Architecture: Block Diffusion Language Model Base Model: Continually pre-trained from the highly efficient Tri-7B model. Korean Language Leadership Trida-7B-Preview sets a new benchmark for generative models in the region. To our knowledge, it is the: - First Block Diffusion Language Model to be openly released in Korea. - Best-performing diffusion language model in Korean among similar model sizes. This model is a significant step forward for the Korean LLM community, demonstrating the effectiveness of the Block Diffusion paradigm for complex, multilingual tasks. ### Key Highlights * **Block Diffusion Architecture**: Trida-7B-Preview leverages the **Block Diffusion** architecture, combining the strengths of **parallelized diffusion generation** with **autoregressive dependencies** for improved efficiency, control, and flexible-length sequence generation. * **Multilingual Leadership**: Specially optimized for **Korean, English, and Japanese**, offering robust performance across all three languages. * **Korean First**: To our knowledge, Trida-7B-Preview is the **first Block Diffusion Language Model** to be openly released in Korea. * **Best-in-Class Korean Performance**: It is the **best-performing diffusion language model in Korean** among models of similar size, setting a new benchmark for generative models in the region. ### Model Specifications #### Trida-7B-Preview - Type: Block Diffusion Language Model - Training Stage: Pre-training & Post-training - Architecture: Transformer Decoder with RoPE, SwiGLU, RMSNorm - Number of Parameters: 7.76B - Number of Layers: 32 - Number of Attention Heads: 32 - Context Length: 4,096 - Vocab Size: 128,256 #### 🔄 Training and Methodology We followed the methodology outlined in the Fast-dLLM-v2 approach (as seen in the model: Efficient-Large-Model/Fast_dLLM_v2_7B [https://huggingface.co/Efficient-Large-Model/Fast_dLLM_v2_7B]). Continual Pre-training from Tri-7B: Trida-7B-Preview was continually pre-trained starting from our proprietary model, trillionlabs/Tri-7B. This process was executed using a Block Diffusion training paradigm to transition the efficient base model into a highly capable generative model. ## 🚀 Quickstart ```python from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "trillionlabs/Trida-7B-Preview" model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype="auto", device_map="auto", trust_remote_code=True ) tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True) prompt = "Hey Trida. Why don'y you try that?" messages = [ {"role": "system", "content": "You are Trida, created by TrillionLabs. You are a helpful assistant."}, {"role": "user", "content": prompt} ] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) inputs = tokenizer([text], return_tensors="pt").to(model.device) # Fast-dLLM v2 style parallel decoding gen_ids = model.generate( inputs["input_ids"], tokenizer=tokenizer, max_new_tokens=2048, small_block_size=8, threshold=0.9, ) response = tokenizer.decode( gen_ids[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True ) print(response) ``` You can also checkout our repo (https://github.com/trillion-labs/Fast-dLLM-Trida) for evaluation and demo. --- ## Evaluation We evaluated Trida-7B-Preview across a comprehensive suite of benchmarks assessing general reasoning, knowledge recall, coding abilities, mathematical reasoning, and instruction-following capabilities.
Full evaluation settings | Benchmark | Language | Evaluation Setting | Metric | |:----------|:---------|:------------------|:-------| | **General Reasoning and Factuality** | | | | | • xwinograd_en | English | 0-shot | accuracy | | • xwinograd_jp | Japanese | 0-shot | accuracy | | • KoBEST | Korean | 5-shot | accuracy | | **Knowledge and Reasoning** | | | | | • KMMLU | Korean | 5-shot | accuracy | | • MMLU | English | 5-shot | accuracy | | • Global-MMLU-Lite-en | English | 5-shot | accuracy | | • Global-MMLU-Lite-ko | English | 5-shot | accuracy | | • Global-MMLU-Lite-ja | English | 5-shot | accuracy | | **Coding** | | | | | • HumanEval | English | 0-shot | pass@1 | | • MBPPPlus | English | 0-shot | pass@1 | | **Mathematical Reasoning** | | | | | • GSM8k | English | 0-shot, CoT | exact-match | | • KoGSM8k | Korean | 0-shot, CoT | exact-match | | • MATH500 | English | 0-shot, CoT | exact-match | | **Instruction Following and Chat** | | | | | • IFEval | English | 0-shot | strict-prompt | | • koIFEval | Korean | 0-shot | strict-prompt |
### Benchmark Results ### General Reasoning and Factuality | Benchmark | Tria-7B-Preview | | --- | --- | | KoBEST | 74.08 | | KMMLU | 50.28 | | MMLU | 67.23 | | Global-MMLU-Lite-en | 73.5 | | Global-MMLU-Lite-ko | 64.25 | | xwinograd_en | 69.81 | | xwinograd_jp | 64.75 | ### Coding | Benchmark | Tria-7B-Preview | | --- | --- | | HumanEval | 35.98 | | MBPPPlus | 42.59 | ### Mathematical Reasoning | Benchmark | Trida-7B-Preview | | --- | --- | | GSM8k | 50.42 | | KoGSM8k | 51.18 | | MATH500 | 24.4 | ### Instruction Following | Benchmark | Trida-7B-Preview | | --- | --- | | IFEval | 63.31 | | koIFEval | 68.6 | ## Limitations - Language Support: The model is optimized for English, Korean, and Japanese. Usage with other languages may result in degraded performance. - Knowledge Cutoff: The model's information is limited to data available up to Febuary, 2025. ## License This model is licensed under the Apache License 2.0. ## Contact For inquiries, please contact: info@trillionlabs.co