https://huggingface.co/NurtureAI/Starling-LM-11B-alpha-v1

This is Berkeley’s model: Starling-LM-7B-alpha with the size of model increased to 11B from 7B.
Special thanks to user Undi95 for their mistral passthrough explanation with cg123’s mergekit, Berkeley of course for Starling-LM-7B-alpha, and also everyone contributing to open source AI development.

Together we are strong!

The performance of this model will increase drastically as it is further fine tuned with the newly added layers.

AWQ version and GGUF version coming soon!

  • LyPretoB
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 year ago

    I saw their 7B model closing in on gpt-4 scores in some benchmarks which is absolutely wild but also sus

  • perlthoughtsOPB
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 year ago

    you can now download it with lmstudio. be sure to use the openchat prompt template.

  • perlthoughtsOPB
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 year ago

    gguf files have finished uploading for all llama.cpp users.

  • Creative_Bottle_3225B
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 year ago

    I tried this model a little while ago with LM Studio and I noticed that it does not have GPU acceleration. Sin

  • perlthoughtsOPB
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 year ago

    I noticed a lot of responses about the mergekit configuration i used to copy layers of 7b model of mistral to 11b. Here is my config.yml for mergekit (link in post description):

    slices:
      - sources:
        - model: maywell/Synatra-7B-v0.3-RP
          layer_range: [0, 24]
      - sources:
        - model: maywell/Synatra-7B-v0.3-RP
          layer_range: [8, 32]
    merge_method: passthrough
    dtype: float16
    
  • perlthoughtsOPB
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 year ago

    be sure after you set new default template in lm studio you reload the app delete the chats and reload model there is some sort of bug in that software thaf is extremely annoying hope that helps.

  • perlthoughtsOPB
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 year ago

    i updated configuration again for lmstudio config in gguf repo on huggingface.

  • perlthoughtsOPB
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 year ago

    Last example, until i’m introduced to another issue in the generation.

    Explain how a solid state battery is made in detail.

     A solid-state battery is an emerging type of battery that uses a solid electrolyte instead of a liquid or gel-based one, which is commonly used in traditional batteries like lithium-ion batteries. The solid-state design offers several advantages over conventional batteries, such as improved safety, higher energy density, and longer lifespan. Here's a detailed explanation of how a solid-state battery is made:
    
    1. Electrode preparation: The first step in making a solid-state battery involves preparing the anode (negative electrode) and cathode (positive electrode). Common materials used for these electrodes include lithium, silicon, or other metal oxides. These materials are typically mixed with conductive additives like carbon to enhance their electrical properties.
    
    2. Electrolyte formation: The solid-state battery uses a solid electrolyte, which is usually made from ceramic materials such as lithium-ion conductors like Li7-xLa3-y(PO4)3 (LFP), or other solid-state materials that can facilitate the movement of ions between the anode and cathode. The electrolyte must have a high ionic conductivity while maintaining a stable structure to prevent unwanted reactions with the electrodes.
    
    3. Electrode coating: After preparing the electrodes and electrolytes, they are coated onto thin metal or plastic substrates. This process involves depositing a thin layer of the material onto the substrate using techniques such as spraying, printing, or coating methods. The thickness of these layers is critical to ensure efficient ion transport and maintain battery performance.
    
    4. Assembly: Once the electrodes and electrolytes are prepared, they are assembled into a battery structure. This typically involves stacking the anode, solid-state electrolyte, and cathode together in a layered configuration. The layers can be held together using adhesive materials or other bonding techniques to ensure electrical contact between the components.
    
    5. Sealing: To prevent external contaminants from entering the battery and causing degradation, the assembled layers are sealed with a protective layer such as an encapsulating material or a thin film. This seal also helps maintain the integrity of the solid-state electrolyte and prevents unwanted reactions between the electrodes.
    
    6. Final processing: After assembly and sealing, the battery is subjected to various tests and processes to ensure its performance, safety, and reliability. These tests may include cycling tests (charging and discharging) to evaluate the battery's capacity and lifespan, as well as thermal and mechanical stress tests to assess its durability under different conditions.
    
    7. Battery packaging: Once the solid-state battery has passed all necessary tests and evaluations, it is packaged in a protective casing or housing that protects the battery from external impacts and environmental factors. The final product can then be integrated into various applications such as electric vehicles, portable electronics, or energy storage systems.
    
    Overall, solid-state batteries have the potential to revolutionize the battery industry due to their superior performance characteristics and safety features. However, significant challenges still need to be addressed, including improving ionic conductivity, reducing manufacturing costs, and ensuring long-term stability of the materials used in these batteries.
    
  • perlthoughtsOPB
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 year ago

    Another good example:

    Explain how a rocket engine works in detail. Use specific examples where necessary.

    A rocket engine is a propulsion device that uses the principles of Newton's third law of motion and conservation of momentum to generate thrust by expelling a high-speed jet of gas or other fluid. The basic principle behind a rocket engine is that when a mass is accelerated in one direction, an equal and opposite force is applied in the opposite direction.
    
    Here's a detailed explanation of how a rocket engine works:
    
    1. Combustion chamber: The rocket engine consists of a combustion chamber where fuel (usually a mixture of oxygen and hydrogen) and oxidizer are mixed and ignited. This process is called combustion, and it generates a high-pressure, high-temperature gas mixture known as the propellant.
    
    2. Nozzle: The hot, high-pressure gas mixture exits the combustion chamber through a converging-diverging section of the engine called the nozzle. The nozzle's design helps to increase the speed and pressure of the gas as it expands, which in turn increases the efficiency of the rocket engine.
    
    3. Newton's third law: According to Newton's third law of motion, every action has an equal and opposite reaction. In the case of a rocket engine, the acceleration of the propellant out of the nozzle creates an equal and opposite force on the rocket itself, causing it to move in the opposite direction. This is how the rocket generates thrust.
    
    4. Conservation of momentum: The conservation of momentum principle states that the total momentum of a closed system remains constant if no external forces are acting upon it. In a rocket engine, the momentum of the propellant entering the combustion chamber (which is initially at rest) is equal to the momentum of the expelled gas leaving the nozzle. This ensures that the rocket continues to accelerate as long as fuel is being consumed.
    
    5. Rocket types: There are several types of rocket engines, including:
    
    - Liquid-fueled: These engines use liquid fuels and oxidizers, such as hydrogen and oxygen, which are stored separately in tanks. Examples include the Space Shuttle's Rocketdyne RS-28 engine and the Falcon 9's Merlin engine.
    
    - Solid-fueled: In these engines, the fuel and oxidizer are combined into a solid, composite material. When ignited, the entire solid propellant burns uniformly from the center to the outer surface. Examples include the Space Shuttle's Solid Rocket Booster (SRB) and the early Saturn V rocket engines.
    
    - Hybrid: These engines use a combination of liquid and solid fuels, with the oxidizer stored in a separate tank. The fuel and oxidizer are fed into the combustion chamber separately, but they burn together to produce thrust. Examples include the SpaceShipTwo's hybrid engine and some experimental rocket engines.
    
    In summary, a rocket engine works by igniting a mixture of fuel and oxidizer in a combustion chamber, which generates high-pressure gas. The gas is then expelled through a nozzle at high speeds, creating thrust according to Newton's third law and conservation of momentum principles. Different types of rocket engines use various combinations of fuels and oxidizers to achieve the desired performance characteristics.