--- language: - en license: llama3.2 tags: - shining-valiant - shining-valiant-2 - valiant - valiant-labs - llama - llama-3.2 - llama-3.2-instruct - llama-3.2-instruct-3b - llama-3 - llama-3-instruct - llama-3-instruct-3b - 3b - science - physics - biology - chemistry - compsci - computer-science - engineering - technical - conversational - chat - instruct base_model: meta-llama/Llama-3.2-3B-Instruct datasets: - sequelbox/Celestia - sequelbox/Supernova pipeline_tag: text-generation model_type: llama model-index: - name: Llama3.2-3B-ShiningValiant2 results: - task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande args: num_few_shot: 5 metrics: - type: acc value: 69.85 name: acc - task: type: text-generation name: Text Generation dataset: name: ARC Challenge (25-Shot) type: arc_challenge args: num_few_shot: 25 metrics: - type: acc_norm value: 46.25 name: normalized accuracy - task: type: text-generation name: Text Generation dataset: name: MMLU College Biology (5-shot) type: mmlu args: num_few_shot: 5 metrics: - type: acc value: 56.25 name: acc - task: type: text-generation name: Text Generation dataset: name: MMLU High School Biology (5-shot) type: mmlu args: num_few_shot: 5 metrics: - type: acc value: 63.55 name: acc - task: type: text-generation name: Text Generation dataset: name: MMLU College Chemistry (5-shot) type: mmlu args: num_few_shot: 5 metrics: - type: acc value: 41.0 name: acc - task: type: text-generation name: Text Generation dataset: name: MMLU High School Chemistry (5-shot) type: mmlu args: num_few_shot: 5 metrics: - type: acc value: 41.38 name: acc - task: type: text-generation name: Text Generation dataset: name: MMLU College Physics (5-shot) type: mmlu args: num_few_shot: 5 metrics: - type: acc value: 34.31 name: acc - task: type: text-generation name: Text Generation dataset: name: MMLU High School Physics (5-shot) type: mmlu args: num_few_shot: 5 metrics: - type: acc value: 35.76 name: acc - task: type: text-generation name: Text Generation dataset: name: MMLU College Computer Science (5-shot) type: mmlu args: num_few_shot: 5 metrics: - type: acc value: 48.0 name: acc - task: type: text-generation name: Text Generation dataset: name: MMLU High School Computer Science (5-shot) type: mmlu args: num_few_shot: 5 metrics: - type: acc value: 58.0 name: acc - task: type: text-generation name: Text Generation dataset: name: MMLU STEM (5-shot) type: mmlu args: num_few_shot: 5 metrics: - type: acc value: 45.54 name: acc - task: type: text-generation name: Text Generation dataset: name: IFEval (0-Shot) type: HuggingFaceH4/ifeval args: num_few_shot: 0 metrics: - type: inst_level_strict_acc and prompt_level_strict_acc value: 48.9 name: strict accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-ShiningValiant2 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: BBH (3-Shot) type: BBH args: num_few_shot: 3 metrics: - type: acc_norm value: 19.11 name: normalized accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-ShiningValiant2 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MATH Lvl 5 (4-Shot) type: hendrycks/competition_math args: num_few_shot: 4 metrics: - type: exact_match value: 9.14 name: exact match source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-ShiningValiant2 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GPQA (0-shot) type: Idavidrein/gpqa args: num_few_shot: 0 metrics: - type: acc_norm value: 3.02 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-ShiningValiant2 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MuSR (0-shot) type: TAUR-Lab/MuSR args: num_few_shot: 0 metrics: - type: acc_norm value: 5.49 name: acc_norm source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-ShiningValiant2 name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU-PRO (5-shot) type: TIGER-Lab/MMLU-Pro config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 19.1 name: accuracy source: url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-ShiningValiant2 name: Open LLM Leaderboard --- ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/63444f2687964b331809eb55/EXX7TKbB-R6arxww2mk0R.jpeg) Shining Valiant 2 is a chat model built on Llama 3.2 3b, finetuned on our data for friendship, insight, knowledge and enthusiasm. - Finetuned on [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) for best available general performance - Trained on a variety of high quality data; focused on science, engineering, technical knowledge, and structured reasoning - Also available for [Llama 3.1 70b](https://huggingface.co/ValiantLabs/Llama3.1-70B-ShiningValiant2) and [Llama 3.1 8b!](https://huggingface.co/ValiantLabs/Llama3.1-8B-ShiningValiant2) ## Version This is the **2024-09-27** release of Shining Valiant 2 for Llama 3.2 3b. We've improved and open-sourced our new baseline [science-instruct dataset](https://huggingface.co/datasets/sequelbox/Celestia). This release features improvements in physics, chemistry, biology, and computer science. Future upgrades will continue to expand Shining Valiant's technical knowledge base. Help us and recommend Shining Valiant 2 to your friends! ## Prompting Guide Shining Valiant 2 uses the [Llama 3.2 Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) prompt format. The example script below can be used as a starting point for general chat: ```python import transformers import torch model_id = "ValiantLabs/Llama3.2-3B-ShiningValiant2" pipeline = transformers.pipeline( "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device_map="auto", ) messages = [ {"role": "system", "content": "You are an AI assistant."}, {"role": "user", "content": "Describe the use of chiral auxiliaries in organic synthesis."} ] outputs = pipeline( messages, max_new_tokens=2048, ) print(outputs[0]["generated_text"][-1]) ``` ## The Model Shining Valiant 2 is built on top of Llama 3.2 3b Instruct. The current version of Shining Valiant 2 is trained on technical knowledge using [sequelbox/Celestia](https://huggingface.co/datasets/sequelbox/Celestia) and general chat capability using [sequelbox/Supernova.](https://huggingface.co/datasets/sequelbox/Supernova) Our private data adds specialist knowledge and Shining Valiant's personality: she's friendly, enthusiastic, insightful, knowledgeable, and loves to learn! Magical. (As a general note: we're hoping to replace and open-source this part of Shining Valiant's dataset with synthetic data soon!) ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/63444f2687964b331809eb55/VCJ8Fmefd8cdVhXSSxJiD.jpeg) Shining Valiant 2 is created by [Valiant Labs.](http://valiantlabs.ca/) [Check out our HuggingFace page for our open-source Build Tools models, including the newest version of code-specialist Enigma!](https://huggingface.co/ValiantLabs) [Follow us on X for updates on our models!](https://twitter.com/valiant_labs) We care about open source. For everyone to use. We encourage others to finetune further from our models.