--- license: apache-2.0 license_link: https://huggingface.co/Freedman/Qybera2.5-0.5B-Instruct/blob/main/LICENSE language: - en - es - ch pipeline_tag: text2text-generation tags: - chat library_name: transformers datasets: - facebook/natural_reasoning new_version: Qybera/Qybera2.6-0.5B-instruct --- # Qybera2.5-0.5B-Instruct ## Introduction Qybera2.5 is the latest series of Qybera large language models. For Qybera2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qybera2.5 brings the following improvements upon Qybera2: - Significantly **more knowledge** and has greatly improved capabilities in **coding** and **mathematics**, thanks to our specialized expert models in these domains. - Significant improvements in **instruction following**, **generating long texts** (over 8K tokens), **understanding structured data** (e.g, tables), and **generating structured outputs** especially JSON. **More resilient to the diversity of system prompts**, enhancing role-play implementation and condition-setting for chatbots. - **Long-context Support** up to 128K tokens and can generate up to 8K tokens. - **Multilingual support** for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more. **This repo contains the instruction-tuned 0.5B Qybera2.5 model**, which has the following features: - Type: Causal Language Models - Training Stage: Pretraining & Post-training - Architecture: transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias and tied word embeddings - Number of Parameters: 0.5B - Number of Paramaters (Non-Embedding): 0.48B - Number of Layers: 24 - Number of Attention Heads (GQA): 14 for Q and 2 for KV - Context Length: Full 32,768 tokens and generation 8192 tokens For more details, please refer to our [blog](https://Qyberalm.github.io/blog/Qybera2.5/), [GitHub](https://github.com/QyberaLM/Qybera2.5), and [Documentation](https://Qybera.readthedocs.io/en/latest/). ## Requirements The code of Qybera2.5 has been in the latest Hugging face `transformers` and we advise you to use the latest version of `transformers`. With `transformers<4.37.0`, you will encounter the following error: ``` KeyError: 'Qybera2' ``` ## Quickstart Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents. ```python from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "Qybera/Qybera2.5-0.5B-Instruct" model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype="auto", device_map="auto" ) tokenizer = AutoTokenizer.from_pretrained(model_name) prompt = "Give me a short introduction to large language model." messages = [ {"role": "system", "content": "You are Qybera, created by worldaicorp. You are a helpful assistant."}, {"role": "user", "content": prompt} ] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) model_inputs = tokenizer([text], return_tensors="pt").to(model.device) generated_ids = model.generate( **model_inputs, max_new_tokens=512 ) generated_ids = [ output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids) ] response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] ``` ## Evaluation & Performance Detailed evaluation results are reported in this [📑 blog](https://Qyberalm.github.io/blog/Qybera2.5/). For requirements on GPU memory and the respective throughput, see results [here](https://Qybera.readthedocs.io/en/latest/benchmark/speed_benchmark.html). ```