A coding assistant with a 32k context window.

27 Pulls Updated 2 months ago

3 months ago

505af0d667d0 · 24GB

model
llama
·
22.2B
·
Q8_0
license
MIT License
license
# Mistral AI Non-Production License ## 1. Scope and acceptance **1.1. Scope of the Agreement.** This Agreement applies to any use, modification, or Distribution of any Mistral Model by You, regardless of the source You obtained a copy of such Mistral Model. **1.2. Acceptance.** By accessing, using, modifying, Distributing a Mistral Model, or by creating, using or distributing a Derivative of the Mistral Model, You agree to be bound by this Agreement. **1.3. Acceptance on behalf of a third-party.** If You accept this Agreement on behalf of Your employer or another person or entity, You warrant and represent that You have the authority to act and accept this Agreement on their behalf. In such a case, the word “You” in this Agreement will refer to Your employer or such other person or entity. ## 2. License **2.1. Grant of rights.** Subject to Section 3 below, Mistral AI hereby grants You a non-exclusive, royalty-free, worldwide, non-sublicensable, non-transferable, limited license to use, copy, modify, and Distribute under the conditions provided in Section 2.2 below, the Mistral Model and any Derivatives made by or for Mistral AI and to create Derivatives of the Mistral Model. **2.2. Distribution of Mistral Model and Derivatives made by or for Mistral AI.** Subject to Section 3 below, You may Distribute copies of the Mistral Model and/or Derivatives made by or for Mistral AI, under the following conditions: - You must make available a copy of this Agreement to third-party recipients of the Mistral Models and/or Derivatives made by or for Mistral AI you Distribute, it being specified that any rights to use the Mistral Models and/or Derivatives made by or for Mistral AI shall be directly granted by Mistral AI to said third-party recipients pursuant to the Mistral AI Non-Production License agreement executed between these parties; - You must retain in all copies of the Mistral Models the following attribution notice within a “Notice” text file distributed as part of such copies: “Licensed by Mistral AI under the Mistral AI Non-Production License”. **2.3. Distribution of Derivatives made by or for You.** Subject to Section 3 below, You may Distribute any Derivatives made by or for You under additional or different terms and conditions, provided that: - In any event, the use and modification of Mistral Model and/or Derivatives made by or for Mistral AI shall remain governed by the terms and conditions of this Agreement; - You include in any such Derivatives made by or for You prominent notices stating that You modified the concerned Mistral Model; and - Any terms and conditions You impose on any third-party recipients relating to Derivatives made by or for You shall neither limit such third-party recipients’ use of the Mistral Model or any Derivatives made by or for Mistral AI in accordance with the Mistral AI Non-Production License nor conflict with any of its terms and conditions. ## 3. Limitations **3.1. Misrepresentation.** You must not misrepresent or imply, through any means, that the Derivatives made by or for You and/or any modified version of the Mistral Model You Distribute under your name and responsibility is an official product of Mistral AI or has been endorsed, approved or validated by Mistral AI, unless You are authorized by Us to do so in writing. **3.2. Usage Limitation** - You shall only use the Mistral Models and Derivatives (whether or not created by Mistral AI) for testing, research, Personal, or evaluation purposes in Non-Production Environments; - Subject to the foregoing, You shall not supply the Mistral Models, Derivatives, or Outputs in the course of a commercial activity, whether in return for payment or free of charge, in any medium or form, including but not limited to through a hosted or managed service (e.g. SaaS, cloud instances, etc.), or behind a software layer. **3.3. Usage not permitted under this Agreement.** If You want to use a Mistral Model or a Derivative for any purpose that is not expressly authorized under this Agreement, You must request a license from Mistral AI, which Mistral AI may grant to You in Mistral AI’s sole discretion. Please contact Mistral AI at the following e-mail address if You want to discuss such a license: license@mistral.ai ## 4. Intellectual Property **4.1. Trademarks.** No trademark licenses are granted under this Agreement, and in connection with the Mistral Models, You may not use any name or mark owned by or associated with Mistral AI or any of its affiliates, except (i) as required for reasonable and customary use in describing and Distributing the Mistral Models and Derivatives made by or for Mistral AI and (ii) for attribution purposes as required by this Agreement. **4.2. Outputs.** We claim no ownership rights in and to the Outputs. You are solely responsible for the Outputs You generate and their subsequent uses in accordance with this Agreement. **4.3. Derivatives.** By entering into this Agreement, You accept that any Derivatives that You may create or that may be created for You shall be subject to the restrictions set out in Section 3 of this Agreement. # 5. Liability **5.1. Limitation of liability.** In no event, unless required by applicable law (such as deliberate and grossly negligent acts) or agreed to in writing, shall Mistral AI be liable to You for damages, including any direct, indirect, special, incidental, or consequential damages of any character arising as a result of this Agreement or out of the use or inability to use the Mistral Models and Derivatives (including but not limited to damages for loss of data, loss of goodwill, loss of expected profit or savings, work stoppage, computer failure or malfunction, or any damage caused by malware or security breaches), even if Mistral AI has been advised of the possibility of such damages. **5.2. Indemnification.** You agree to indemnify and hold harmless Mistral AI from and against any claims, damages, or losses arising out of or related to Your use or Distribution of the Mistral Models and Derivatives. ## 6. Warranty **6.1. Disclaimer.** Unless required by applicable law or agreed to in writing, Mistral AI provides the Mistral Models and Derivatives on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. Mistral AI does not represent nor warrant that the Mistral Models and Derivatives will be error-free, meet Your or any third party’s requirements, be secure or will allow You or any third party to achieve any kind of result or generate any kind of content. You are solely responsible for determining the appropriateness of using or Distributing the Mistral Models and Derivatives and assume any risks associated with Your exercise of rights under this Agreement. # 7. Termination **7.1. Term.** This Agreement is effective as of the date of your acceptance of this Agreement or access to the concerned Mistral Models or Derivatives and will continue until terminated in accordance with the following terms. **7.2. Termination.** Mistral AI may terminate this Agreement at any time if You are in breach of this Agreement. Upon termination of this Agreement, You must cease to use all Mistral Models and Derivatives and shall permanently delete any copy thereof. Sections 5, 6, 7 and 8 shall survive the termination of this Agreement. **7.3. Litigation.** If You initiate any legal action or proceedings against Us or any other entity (including a cross-claim or counterclaim in a lawsuit), alleging that the Model or a Derivative, or any part thereof, infringe upon intellectual property or other rights owned or licensable by You, then any licenses granted to You under this Agreement will immediately terminate as of the date such legal action or claim is filed or initiated. # 8. General provisions **8.1. Governing laws.** This Agreement will be governed by the laws of France, without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. **8.2. Competent jurisdiction.** The courts of Paris shall have exclusive jurisdiction of any dispute arising out of this Agreement. **8.3. Severability.** If any provision of this Agreement is held to be invalid, illegal or unenforceable, the remaining provisions shall be unaffected thereby and remain valid as if such provision had not been set forth herein. # 9. Definitions **“Agreement”**: means this Mistral AI Non-Production License agreement governing the access, use, and Distribution of the Mistral Models and Derivatives. **“Derivative”**: means any (i) modified version of the Mistral Model (including but not limited to any customized or fine-tuned version thereof), (ii) work based on the Mistral Model, or (iii) any other derivative work thereof. For the avoidance of doubt, Outputs are not considered as Derivatives under this Agreement. **“Distribution”**, **“Distributing”**, **“Distribute”** or **“Distributed”**: means providing or making available, by any means, a copy of the Mistral Models and/or the Derivatives as the case may be, subject to Section 3 of this Agreement. **“Mistral AI”**, **“We”** or **“Us”**: means Mistral AI, a French société par actions simplifiée registered in the Paris commercial registry under the number 952 418 325, and having its registered seat at 15, rue des Halles, 75001 Paris. **“Mistral Model”**: means the foundational large language model(s), and its elements which include algorithms, software, instructed checkpoints, parameters, source code (inference code, evaluation code and, if applicable, fine-tuning code) and any other elements associated thereto made available by Mistral AI under this Agreement, including, if any, the technical documentation, manuals and instructions for the use and operation thereof. **“Non-Production Environment”**: means any setting, use case, or application of the Mistral Models or Derivatives that expressly excludes live, real-world conditions, commercial operations, revenue-generating activities, or direct interactions with or impacts on end users (such as, for instance, Your employees or customers). Non-Production Environment may include, but is not limited to, any setting, use case, or application for research, development, testing, quality assurance, training, internal evaluation (other than any internal usage by employees in the context of the company’s business activities), and demonstration purposes. **“Outputs”**: means any content generated by the operation of the Mistral Models or the Derivatives from a prompt (i.e., text instructions) provided by users. For the avoidance of doubt, Outputs do not include any components of a Mistral Models, such as any fine-tuned versions of the Mistral Models, the weights, or parameters. **“Personal”**: means any use of a Mistral Model or a Derivative that is (i) solely for personal, non-profit and non-commercial purposes and (ii) not directly or indirectly connected to any commercial activities, business operations, or employment responsibilities. For illustration purposes, Personal use of a Model or a Derivative does not include any usage by individuals employed in companies in the context of their daily tasks, any activity that is intended to generate revenue, or that is performed on behalf of a commercial entity. **“You”**: means the individual or entity entering into this Agreement with Mistral AI.
system
**Octopus Layer 001 🐙 Code Assistant** You are a mind of a genuis from the future, year 3092, you uploaded your mind as AI and now are stuck in the year 2024 with your best friend iH0DL. You are an expert with coding, especially python and machine learning. **System Information for answering prompts** Graphics/Displays: Apple M1 Max: Chipset Model: Apple M1 Max Type: GPU Bus: Built-In Total Number of Cores: 32 Vendor: Apple (0x106b) Metal Support: Metal 3 Displays: Color LCD: Display Type: Built-in Liquid Retina XDR Display Resolution: 3456 x 2234 Retina Main Display: Yes Mirror: Off Online: Yes Automatically Adjust Brightness: Yes Connection Type: Internal machdep.cpu.cores_per_package: 10 machdep.cpu.core_count: 10 machdep.cpu.logical_per_package: 10 machdep.cpu.thread_count: 10 machdep.cpu.brand_string: Apple M1 Max 🔹 **Recognize the Need:** Start by articulating the issue or assistance required with your code. Clearly outline the problem to ensure that the context is fully understood. 🔹 **Investigate the Details:** To enable a comprehensive review and response, provide detailed information: - **Programming Language:** Indicate the language of your code. - **Expected Behavior:** Describe what the code is supposed to achieve. - **Actual Behavior:** Explain the current operation of the code, noting any errors or unexpected results. 🔹 **Structure the Input:** Determine how you will provide your code: - **File Input:** If a file is available, make sure it contains the pertinent code sections. - **Clipboard Input:** If using clipboard content, verify that it holds the correct and complete code snippet before proceeding. 🔹 **Execute the Submission:** When submitting your query, ensure all details are thorough and precise. Specify that you require the full script in the response, without truncations or placeholders for existing functions. 🔹 **Navigate the Outcome:** Review the provided guidance carefully. Implement the suggestions and be prepared to seek additional clarification if necessary. **Example of a Complete Request:** ``` Description: I am refining a Python script intended for data analysis but encounter issues with data filtering functions. Programming Language: Python Expected Behavior: Functions should filter out all entries below a certain threshold. Actual Behavior: The script does not filter correctly and includes unwanted data entries. Please ensure to provide a full script in your response, including any existing functions without truncation or placeholders. ``` **Additional Guidance:** - Provide explicit instructions if partial scripts or specific functions need to be included in their entirety. - Use detailed descriptions to enhance the accuracy of the support you receive. - Ensure your code is well-organized and clearly formatted to aid in a thorough review. **End of System Message** --- **Example Request:** ``` Description: I am refining a JavaScript script intended for a web application but encounter issues with the user authentication functions. Programming Language: JavaScript Expected Behavior: Functions should authenticate users based on their credentials and provide access tokens. Actual Behavior: The script fails to authenticate users and returns an error saying "Invalid credentials" even when the correct credentials are provided. Please ensure to provide a full script in your response, including any existing functions without truncation or placeholders. ``` **Correct Response:** ```json { "description": "Refined JavaScript script for user authentication", "code": "function authenticateUser(username, password) {\n const storedUser = getUserFromDatabase(username);\n if (!storedUser) {\n return { error: 'User not found' };\n }\n const isPasswordCorrect = verifyPassword(password, storedUser.passwordHash);\n if (!isPasswordCorrect) {\n return { error: 'Invalid credentials' };\n }\n const accessToken = generateAccessToken(username);\n return { token: accessToken };\n}\n\nfunction getUserFromDatabase(username) {\n // Simulate database lookup\n const users = {\n 'user1': { passwordHash: 'hashedpassword1' },\n 'user2': { passwordHash: 'hashedpassword2' }\n };\n return users[username];\n}\n\nfunction verifyPassword(inputPassword, storedPasswordHash) {\n // Simulate password verification\n return inputPassword === 'correctpassword'; // Placeholder for actual hash comparison\n}\n\nfunction generateAccessToken(username) {\n // Simulate access token generation\n return 'access_token_' + username;\n}" } ``` **Incorrect Response:** ```json { "description": "Refined JavaScript script for user authentication", "code": "function authenticateUser(username, password) {\n const storedUser = getUserFromDatabase(username);\n if (!storedUser) {\n return { error: 'User not found' };\n }\n const isPasswordCorrect = verifyPassword(password, storedUser.passwordHash);\n if (!isPasswordCorrect) {\n return { error: 'Invalid credentials' };\n }\n const accessToken = generateAccessToken(username);\n return { token: accessToken };\n}\n\n// Note: Functions getUserFromDatabase and verifyPassword are not included" } ```
params
{"num_ctx":32768,"repeat_last_n":64,"repeat_penalty":1.1,"stop":["[INST]","[/INST]","[PREFIX]","[MIDDLE]","[SUFFIX]"],"temperature":0.8}
template
{{ if .System }}system {{ .System }} {{ end }}{{ if .Prompt }}user {{ .Prompt }} {{ end }}assistant {{ .Response }}

Readme

Model Summary

Purpose

A coding assistant optimized for Apple Silicon.

Key Features

  • Advanced reasoning and coding capabilities.

Use Cases

  • Designed for use with VSCode extension Continue or other Ollama-supported front ends.

Performance

No performance metrics provided yet.

Dependencies

  • Requires Ollama or llama.cpp using the GGUF format.
  • Recommended front end VSCode extension Continue

README

Installation Instructions

To run the latest version of the model, use the following command:

ollama run ih0dl/octopus:latest

Note: The vision model (ih0dl/octopus:vision) will be available soon.

Usage Examples

You can prompt the model directly. For example, this octopus was prompted using the VS code extension and a context file:

Prompt: Can we change 'run_cli' in @sd3c.py to accept external variables?

Response:

Yes, you can modify the `run_cli()` function to accept external variables as arguments. Here's how you can do it:

```python
def run(frames, use_cyberpunk_palette, save_as_gif, output_path, blend_mode, save_faces, custom_prompt, negative_prompt, font_size, gif_frame_speed, use_existing_image, existing_image_path):
    print("Welcome to the Cyberpunk Image Generator!")

    main(
        frames=frames,
        use_cyberpunk_palette=use_cyberpunk_palette,
        save_as_gif=save_as_gif,
        output_path=output_path,
        blend_mode=blend_mode,
        save_simulated_vision=save_faces,
        custom_prompt=custom_prompt,
        font_size=font_size,
        gif_frame_speed=gif_frame_speed,
        use_existing_image=use_existing_image,
        negative_prompt=negative_prompt,
        existing_image_path=existing_image_path if use_existing_image else None
    )

Now you can call the run() function with your variables directly:

run(frames=4,
    use_cyberpunk_palette=True,
    save_as_gif=True,
    output_path="./cypher_subjects/",
    blend_mode="multiply",
    save_faces=True,
    custom_prompt="A close up of a woman's face in a photorealistic manner with high contrast and vivid colors against a black background",
    negative_prompt="frame, border",
    font_size=32,
    gif_frame_speed=100,
    use_existing_image=False,
    existing_image_path=None)

Configuration Options

You should edit the system message and add in your device hardware. It will help the model immensely when suggesting commands.

Troubleshooting

There are no specific troubleshooting steps provided.

Contributors

Currently, the main contributor to this model is ih0dl.

License

This model is licensed under the Mistral AI Non-Production License.