{"id":14964666,"url":"https://github.com/gallen881/physics_master","last_synced_at":"2025-10-25T08:30:17.897Z","repository":{"id":251477989,"uuid":"837538200","full_name":"gallen881/Physics_Master","owner":"gallen881","description":"Physics Master is a model fine-tuned from llama3-8B-Instruct. It can answer your physics question!","archived":false,"fork":false,"pushed_at":"2024-08-24T15:19:34.000Z","size":22,"stargazers_count":13,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2024-10-10T18:03:56.582Z","etag":null,"topics":["ai","fine-tuning","finetune","finetuning","llama3","llm","physics"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/gallen881.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-08-03T09:18:32.000Z","updated_at":"2024-09-25T01:08:55.000Z","dependencies_parsed_at":"2024-08-24T16:55:20.369Z","dependency_job_id":null,"html_url":"https://github.com/gallen881/Physics_Master","commit_stats":null,"previous_names":["gallen881/physics_master"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gallen881%2FPhysics_Master","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gallen881%2FPhysics_Master/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gallen881%2FPhysics_Master/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gallen881%2FPhysics_Master/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gallen881","download_url":"https://codeload.github.com/gallen881/Physics_Master/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":219866281,"owners_count":16555908,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","fine-tuning","finetune","finetuning","llama3","llm","physics"],"created_at":"2024-09-24T13:33:36.090Z","updated_at":"2025-10-25T08:30:17.555Z","avatar_url":"https://github.com/gallen881.png","language":"Jupyter Notebook","readme":"# Physics Master\n\nPhysics Master is a model finetuned from [unsloth/llama-3-8b-Instruct-bnb-4bit](https://huggingface.co/unsloth/llama-3-8b-Instruct-bnb-4bit) and [ArtifactAI/arxiv-physics-instruct-tune-30k](https://huggingface.co/datasets/ArtifactAI/arxiv-physics-instruct-tune-30k). Here is the python code. The model is open source on [Hugging Face](https://huggingface.co/gallen881/Llama-3-8B-Physics_Master-GGUF).\n\n## How to use?\n\n### Run model on local computer\n\n1. Clone this repo.\n    ```\n    git clone https://github.com/gallen881/Physics_Master.git\n    ```\n2. Move to `Physics_Master`\n    ```\n    cd Physics_Master\n    ```\n3. Install dependencies.\n    ```\n    pip install -r requirements.txt\n    ```\n3. Run `chat.py`.\n    ```\n    python chat.py\n    ```\n\n### Run model on Colab\n\nhttps://colab.research.google.com/github/gallen881/Physics_Master/blob/master/chat.ipynb\n\n## Additional Function\n\nIf want to use WolframAlpha, follow these steps:\n\n1. If don't have a WolframAlpha account, go [here](https://developer.wolframalpha.com/) and create one.\n2. Go [here](https://developer.wolframalpha.com/access) and click **Get an App ID**.\n3. Enter **Name** and **Description**, then select **Full Results API**.\n4. Click **Submit**, then copy the **App ID**.\n5. Run `set_keys.py`, then enter your App ID.\n    ```\n    python set_keys.py\n    ```\n\n# 物理大師\n\n物理大師是基於 [unsloth/llama-3-8b-Instruct-bnb-4bit](https://huggingface.co/unsloth/llama-3-8b-Instruct-bnb-4bit) 和 [ArtifactAI/arxiv-physics-instruct-tune-30k](https://huggingface.co/datasets/ArtifactAI/arxiv-physics-instruct-tune-30k) 微調的模型。這裡存放 Python 腳本。模型開源於 [Hugging Face](https://huggingface.co/gallen881/Llama-3-8B-Physics_Master-GGUF)。\n\n## 如何使用？\n\n### 在本地電腦運行\n\n1. clone 這個 repo\n    ```\n    git clone https://github.com/gallen881/Physics_Master.git\n    ```\n2. 移動目錄到 `Physics_Master`\n    ```\n    cd Physics_Master\n    ```\n3. 安裝依賴\n    ```\n    pip install -r requirements.txt\n    ```\n3. 運行 `chat.py`\n    ```\n    python chat.py\n    ```\n\n### 在 colab 上運行\n\nhttps://colab.research.google.com/github/gallen881/Physics_Master/blob/master/chat.ipynb\n\n## 額外功能\n\n如果想使用 WolframAlpha 的功能，依照以下步驟：\n\n1. 如果沒有 WolframAlpha 帳號，前往[這裡](https://developer.wolframalpha.com/)註冊。\n2. 前往[這裡](https://developer.wolframalpha.com/access) 然後點擊 **Get an App ID**。\n3. 輸入 **Name** 和 **Description** 然後選擇 **Full Results API**。\n4. 點擊 **Submit** 然後複製 **App ID**。\n5. 執行 `set_keys.py` 然後輸入你的 App ID。\n    ```\n    python set_keys.py\n    ```","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgallen881%2Fphysics_master","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgallen881%2Fphysics_master","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgallen881%2Fphysics_master/lists"}