lmstudio-community/stable-code-instruct-3b-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "other",
    "language": [
      "en"
    ],
    "tags": [
      "causal-lm",
      "code"
    ],
    "metrics": [
      "code_eval"
    ],
    "library_name": "transformers",
    "model-index": [
      {
        "name": "stabilityai/stable-code-instruct-3b",
        "results": [
          {
            "task": {
              "type": "text-generation"
            },
            "dataset": {
              "type": "nuprl/MultiPL-E",
              "name": "MultiPL-HumanEval (Python)"
            },
            "metrics": [
              {
                "name": "pass@1",
                "type": "pass@1",
                "value": 32.4,
                "verified": false
              }
            ]
          },
          {
            "task": {
              "type": "text-generation"
            },
            "dataset": {
              "type": "nuprl/MultiPL-E",
              "name": "MultiPL-HumanEval (C++)"
            },
            "metrics": [
              {
                "name": "pass@1",
                "type": "pass@1",
                "value": 30.9,
                "verified": false
              }
            ]
          },
          {
            "task": {
              "type": "text-generation"
            },
            "dataset": {
              "type": "nuprl/MultiPL-E",
              "name": "MultiPL-HumanEval (Java)"
            },
            "metrics": [
              {
                "name": "pass@1",
                "type": "pass@1",
                "value": 32.1,
                "verified": false
              }
            ]
          },
          {
            "task": {
              "type": "text-generation"
            },
            "dataset": {
              "type": "nuprl/MultiPL-E",
              "name": "MultiPL-HumanEval (JavaScript)"
            },
            "metrics": [
              {
                "name": "pass@1",
                "type": "pass@1",
                "value": 32.1,
                "verified": false
              }
            ]
          },
          {
            "task": {
              "type": "text-generation"
            },
            "dataset": {
              "type": "nuprl/MultiPL-E",
              "name": "MultiPL-HumanEval (PHP)"
            },
            "metrics": [
              {
                "name": "pass@1",
                "type": "pass@1",
                "value": 24.2,
                "verified": false
              }
            ]
          },
          {
            "task": {
              "type": "text-generation"
            },
            "dataset": {
              "type": "nuprl/MultiPL-E",
              "name": "MultiPL-HumanEval (Rust)"
            },
            "metrics": [
              {
                "name": "pass@1",
                "type": "pass@1",
                "value": 23,
                "verified": false
              }
            ]
          }
        ]
      }
    ],
    "quantized_by": "bartowski",
    "pipeline_tag": "text-generation",
    "lm_studio": {
      "param_count": "3b",
      "use_case": "coding",
      "release_date": "19-03-2024",
      "model_creator": "stabilityai",
      "prompt_template": "ChatML",
      "system_prompt": "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.",
      "base_model": "stablelm",
      "original_repo": "stabilityai/stable-code-instruct-3b"
    },
    "frontmatter": {
      "license": "other",
      "language": [
        "en"
      ],
      "tags": [
        "causal-lm",
        "code"
      ],
      "metrics": [
        "code_eval"
      ],
      "library_name": [
        "name: stabilityai/stable-code-instruct-3b",
        "task:",
        "name: pass@1",
        "task:",
        "name: pass@1",
        "task:",
        "name: pass@1",
        "task:",
        "name: pass@1",
        "task:",
        "name: pass@1",
        "task:",
        "name: pass@1"
      ],
      "quantized_by": "bartowski",
      "pipeline_tag": "text-generation",
      "lm_studio": []
    },
    "hero_image_url": "",
    "summary": "",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: other\nlanguage:\n- en\ntags:\n- causal-lm\n- code\nmetrics:\n- code_eval\nlibrary_name: transformers\nmodel-index:\n- name: stabilityai/stable-code-instruct-3b\n  results:\n  - task:\n      type: text-generation\n    dataset:\n      type: nuprl/MultiPL-E\n      name: MultiPL-HumanEval (Python)\n    metrics:\n    - name: pass@1\n      type: pass@1\n      value: 32.4\n      verified: false\n  - task:\n      type: text-generation\n    dataset:\n      type: nuprl/MultiPL-E\n      name: MultiPL-HumanEval (C++)\n    metrics:\n    - name: pass@1\n      type: pass@1\n      value: 30.9\n      verified: false\n  - task:\n      type: text-generation\n    dataset:\n      type: nuprl/MultiPL-E\n      name: MultiPL-HumanEval (Java)\n    metrics:\n    - name: pass@1\n      type: pass@1\n      value: 32.1\n      verified: false\n  - task:\n      type: text-generation\n    dataset:\n      type: nuprl/MultiPL-E\n      name: MultiPL-HumanEval (JavaScript)\n    metrics:\n    - name: pass@1\n      type: pass@1\n      value: 32.1\n      verified: false\n  - task:\n      type: text-generation\n    dataset:\n      type: nuprl/MultiPL-E\n      name: MultiPL-HumanEval (PHP)\n    metrics:\n    - name: pass@1\n      type: pass@1\n      value: 24.2\n      verified: false\n  - task:\n      type: text-generation\n    dataset:\n      type: nuprl/MultiPL-E\n      name: MultiPL-HumanEval (Rust)\n    metrics:\n    - name: pass@1\n      type: pass@1\n      value: 23.0\n      verified: false\nquantized_by: bartowski\npipeline_tag: text-generation\nlm_studio:\n  param_count: 3b\n  use_case: coding\n  release_date: 19-03-2024\n  model_creator: stabilityai\n  prompt_template: ChatML\n  system_prompt: A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.\n  base_model: stablelm\n  original_repo: stabilityai/stable-code-instruct-3b\n---\n\n## 💫 Community Model> Stable Code Instruct 3B by Stability AI\n\n*👾 [LM Studio](https://lmstudio.ai) Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on [Discord](https://discord.gg/aPQfnNkxGC)*.\n\n**Model creator:** [Stability AI](https://huggingface.co/stabilityai)<br>\n**Original model**: [stable-code-instruct-3b](https://huggingface.co/stabilityai/stable-code-instruct-3b)<br>\n**GGUF quantization:** provided by [bartowski](https://huggingface.co/bartowski) based on `llama.cpp` release [b2440](https://github.com/ggerganov/llama.cpp/releases/tag/b2440)<br>\n\n## Model Summary: \nStable Code Instruct 3B is part of the Stable Code family, instruction tuned using [Direct Preference Optimization (DPO)](https://arxiv.org/abs/2305.18290) from the base Stable Code 3B model.\nThis model is great for general purpose coversational coding, as well as SQL generation.<br>\n\n## Prompt Template:\n\nChoose the `ChatML` preset in your LM Studio.\n\nUnder the hood, the model will see a prompt that's formatted like so:\n```\n<|im_start|>system\nA chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n```\n\n## Use case and examples\n\nStable Code Instruct 3B is trained primarily on coding, with a bit of conversational tuning to provide some assistant behavior. It also excels at SQL generation. This makes it great for light-weight coding purposes and its size makes it extremely fast for potential code-completion.\n\n### SQL generation with explanation:\n\n```\n<|im_start|>system<br>\nA chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.<|im_end|><br>\n<|im_start|>user<br>\nUsing python, how can I create an SQL table where the primary key is a combination of two columns?<|im_end|><br>\n<|im_start|>assistant<br>\nTo create an SQL table with a composite primary key in Python, you can use the `sqlite3` module. Here's an example code snippet:\n\n    import sqlite3\n    # Connect to the database (or create it if it doesn't exist)\n    conn = sqlite3.connect('example.db')\n    # Create a cursor object to execute SQL commands\n    c = conn.cursor()\n    # Define the table schema with a composite primary key\n    schema = '''\n    CREATE TABLE example_table (\n        column1 TEXT,\n        column2 INTEGER,\n        PRIMARY KEY (column1, column2)\n    );\n    '''\n    # Execute the SQL command to create the table\n    c.execute(schema)\n    # Commit the changes to the database\n    conn.commit()\n    # Close the database connection\n    conn.close()\n\nIn this example, we first import the `sqlite3` module and create a connection to the database (or create it if it doesn't exist). We then create a cursor object to execute SQL commands.\nNext, we define the table schema with a composite primary key using the `CREATE TABLE` command. In this example, the table is named `example_table` and has two columns: `column1` (text data type) and `column2` (integer data type). The `PRIMARY KEY` constraint is used to specify that the combination of `column1` and `column2` should be unique for each row in the table.\nAfter defining the table schema, we execute the SQL command using the cursor object. We then commit the changes to the database and close the database connection.\nNote that this example assumes that you have already installed the `sqlite3` module in your Python environment. If you haven't done so already, you can install it by running the following command in your terminal or command prompt:\n\n    pip install sqlite3\n\nThis will install the `sqlite3` module in your Python environment.<|im_end|>\n```\n\n### General python coding questions:\n\n```\n<|im_start|>system<br>\nA chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.<|im_end|><br>\n<|im_start|>user<br>\nUsing python, how can I create an SQL table where the primary key is a combination of two columns?<|im_end|><br>\n<|im_start|>assistant<br>\nYou can achieve this by using Python's built-in `sort()` function or `sorted()` function. Both these functions allow you to specify multiple sorting conditions. \n\nHere is an example code snippet that demonstrates how to sort a list of integer tuples based on the second item, then the first:\n\n    # Sample list of integer tuples\n    my_list = [(1, 2), (3, 1), (2, 3)]\n    \n    # Sort the list by the second item, then the first\n    my_list.sort(key=lambda x: (x[1], x[0]))))\n    \n    # Print the sorted list\n    print(my_list)\n\nIn this example, we use a lambda function as the `key` argument to the `sort()` function. The lambda function takes each tuple in the list and returns a tuple of the second item and the first item of the original tuple. This way, the tuples are sorted based on the second item first, then by the first item if there is a tie.\n\nThe output of this code will be:\n\n    [(3, 1), (1, 2), (2, 3)]\n\nThis means that the list has been sorted in ascending order based on the second item of each tuple, and if there is a tie, it is resolved by sorting based on the first item of each tuple.<|im_end|>\n```\n\n### General C coding questions:\n\n```\n<|im_start|>system<br>\nA chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.<|im_end|><br>\n<|im_start|>user<br>\n<|im_start|>user\nCan you write a C program that takes two numbers and prints their sum to the console?<|im_end|>\n<|im_start|>assistant\nSure! Here is a simple C program that does exactly what you asked for:\n\n    #include <stdio.h>\n    \n    int main() {\n        int num1, num2, sum;\n    \n        printf(\"Enter first number: \");\n        scanf(\"%d\", &num1);\n    \n        printf(\"Enter second number: \");\n        scanf(\"%d\", &num2);\n    \n        sum = num1 + num2;\n    \n        printf(\"The sum of %d and %d is %d\\n\", num1, num2, sum);\n    \n        return 0;\n    }\n\nThis program first prompts the user to enter two numbers. It then calculates the sum of those two numbers and prints the result to the console.<|im_end|>\n```\n\n## Technical Details\n\nThe base model was trained from the following datasets:\n\n- [tiiuae/falcon-refinedweb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb)\n- [bigcode/the-stack-github-issues](https://huggingface.co/datasets/bigcode/the-stack-github-issues)\n- [bigcode/commitpackft](https://huggingface.co/datasets/bigcode/commitpackft)\n- [bigcode/starcoderdata](https://huggingface.co/datasets/bigcode/starcoderdata)\n- [EleutherAI/proof-pile-2](https://huggingface.co/datasets/EleutherAI/proof-pile-2)\n- [meta-math/MetaMathQA](https://huggingface.co/datasets/meta-math/MetaMathQA)\n\nSpecializing in the following languages:\n- C\n- CPP\n- Java\n- JavaScript\n- CSS\n- Go\n- HTML\n- Ruby\n- Rust\n- Markdown\n- Shell\n- Php\n- Sql\n- R\n- Typescript\n- Python\n- Jupyter-Clean\n- RestructuredText\n\n## Special thanks\n\n🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible.\n\n## Disclaimers\n\nLM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model.  You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models.  LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.\n",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "causal-lm",
    "code",
    "text-generation",
    "en",
    "arxiv:2305.18290",
    "license:other",
    "model-index",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 2,
  "downloads": 239,
  "gated": false,
  "private": false,
  "last_modified": "2024-04-05T01:54:36.000Z",
  "created_at": "2024-04-02T16:50:02.000Z",
  "pipeline_tag": "text-generation",
  "library_name": "transformers"
}

{
  "_id": "660c373adff6856f94966c5c",
  "id": "lmstudio-community/stable-code-instruct-3b-GGUF",
  "modelId": "lmstudio-community/stable-code-instruct-3b-GGUF",
  "sha": "2062591ac6948f6f96eb1dc989ee7fe23e565b19",
  "createdAt": "2024-04-02T16:50:02.000Z",
  "lastModified": "2024-04-05T01:54:36.000Z",
  "author": "lmstudio-community",
  "downloads": 239,
  "likes": 2,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "transformers",
  "siblings_count": 18
}