anyone know of an open source model better than whisper? If not anyone tried training it?

Vvrballer anyone know of an open source model better than whisper? If not anyone tried tra...

I

Depends. Nvidia's Parakeet is quite good at noisy audio (far better than Whisper in my experience). Haven't tried training/finetuning it but the base model is quite good.

I

Isaac McFadyen•6/24/24, 2:34 AM

Parakeet has two versions - one with no punctuation that is best for accuracy (but is missing punctuation) and one that has punctuation like Whisper that has a little less accuracy.

I

Isaac McFadyen•6/24/24, 2:35 AM

If you go with the one that doesn't have punctuation there are other models designed to take text as input and add punctuation that you can run on the text after.

G

German•6/24/24, 5:17 PM

What's the highest token count LLM available on workers ai?

C

codebam•6/25/24, 10:24 PM

I get this error after updating cloudflare-types https://p.seanbehan.ca/d337e

C

codebam•6/25/24, 10:24 PM

Argument of type '"@hf/thebloke/deepseek-coder-6.7b-instruct-awq"' is not assignable to parameter of type 'BaseAiImageToTextModels'. typescript (2769) [84, 37]

Argument of type '"@hf/thebloke/deepseek-coder-6.7b-instruct-awq"' is not assignable to parameter of type 'BaseAiImageToTextModels'. typescript (2769) [84, 37]

Argument of type '"@hf/thebloke/deepseek-coder-6.7b-instruct-awq"' is not assignable to parameter of type 'BaseAiImageToTextModels'. typescript (2769) [84, 37]

Argument of type '"@hf/thebloke/deepseek-coder-6.7b-instruct-awq"' is not assignable to parameter of type 'BaseAiImageToTextModels'. typescript (2769) [84, 37]

C

codebam•6/25/24, 10:28 PM

the code still works if I

// @ts-expect-error

// @ts-expect-error

// @ts-expect-error

// @ts-expect-error

Ccodebam I get this error after updating cloudflare-types https://p.seanbehan.ca/d337e

K

kian•6/25/24, 11:07 PM

What version of workers-types?

Kkian What version of workers-types?

C

codebam•6/26/24, 12:36 AM

4.20240620.0

GGerman What's the highest token count LLM available on workers ai?

R

Raylight•6/26/24, 10:17 AM

Token count as in context window? qwen1.5-7b-chat-awq can handle a context of ~20k tokens, qwen1.5-14b-chat-awq ~7.5k, and llama-3-8b-instruct-awq ~8k. (Based on my testing.) Those are also limits for the total number of tokens, including output.

R

Raylight•6/26/24, 12:40 PM

Hmm.. interesting..

@cf/mistral/mistral-7b-instruct-v0.2-lora

@cf/mistral/mistral-7b-instruct-v0.2-lora

@cf/mistral/mistral-7b-instruct-v0.2-lora

@cf/mistral/mistral-7b-instruct-v0.2-lora has a context (and total limit) of ~15k tokens and you don't need a LoRA to run it.

云

云•6/27/24, 6:52 AM

huh i tried to pass number array as image to dreamshaper

云

云•6/27/24, 6:52 AM

but got the error

3010: Invalid or incomplete input for the model: model returned: [request id: 41fff8e6-617c-439f-a093-f02bfa2d45bb] unexpected shape for input 'image' for model 'dreamshaper-8-lcm'. Expected [1], got [1,1048265].

3010: Invalid or incomplete input for the model: model returned: [request id: 41fff8e6-617c-439f-a093-f02bfa2d45bb] unexpected shape for input 'image' for model 'dreamshaper-8-lcm'. Expected [1], got [1,1048265].

3010: Invalid or incomplete input for the model: model returned: [request id: 41fff8e6-617c-439f-a093-f02bfa2d45bb] unexpected shape for input 'image' for model 'dreamshaper-8-lcm'. Expected [1], got [1,1048265].

3010: Invalid or incomplete input for the model: model returned: [request id: 41fff8e6-617c-439f-a093-f02bfa2d45bb] unexpected shape for input 'image' for model 'dreamshaper-8-lcm'. Expected [1], got [1,1048265].

Y

yolossn•6/27/24, 10:30 AM

Hey folks,
I am getting authentication errors when using the workers AI, the curl and python requests that is auto generated also is failing.
{'success': False, 'errors': [{'code': 10000, 'message': 'Authentication error'}]}

云云 huh i tried to pass number array as image to dreamshaper

R

Raylight•6/27/24, 11:48 AM

@cf/lykon/dreamshaper-8-lcm

@cf/lykon/dreamshaper-8-lcm

@cf/lykon/dreamshaper-8-lcm

@cf/lykon/dreamshaper-8-lcmdoesn't support passing an image. try

@cf/runwayml/stable-diffusion-v1-5-img2img

@cf/runwayml/stable-diffusion-v1-5-img2img

@cf/runwayml/stable-diffusion-v1-5-img2img

@cf/runwayml/stable-diffusion-v1-5-img2img if you want to do image-to-image.

PPerry Sahnow Is it possible to list all models in a similar fashion to the wrangler command s...

V

Victor•6/28/24, 7:26 PM

API call to the cf: https://developers.cloudflare.com/api/operations/workers-ai-search-model
If you care about custom upload loras: https://developers.cloudflare.com/api/operations/workers-ai-list-finetunes
public loras: https://developers.cloudflare.com/api/operations/workers-ai-list-public-finetunes

Cloudflare API Documentation

Interact with Cloudflare's products and services via the Cloudflare API

Cloudflare API Documentation

Interact with Cloudflare's products and services via the Cloudflare API

Cloudflare API Documentation

Interact with Cloudflare's products and services via the Cloudflare API

V

Victor•6/28/24, 7:30 PM

You could also turn it into a ci build step that runs on a schedule and include it in your release
I did it here in GA in bash: https://github.com/demosjarco/matt-ai/blob/production/.github/workflows/ai-catalog.yml
End result (json): https://github.com/demosjarco/matt-ai/blob/production/shared/workers-ai-catalog.json
End result (ts): https://github.com/demosjarco/matt-ai/blob/production/shared/workers-ai-catalog.ts

GitHub

matt-ai/.github/workflows/ai-catalog.yml at production · demosjarco...

Magically All The Things AI. Contribute to demosjarco/matt-ai development by creating an account on GitHub.

GitHub

matt-ai/shared/workers-ai-catalog.json at production · demosjarco/m...

Magically All The Things AI. Contribute to demosjarco/matt-ai development by creating an account on GitHub.

GitHub

matt-ai/shared/workers-ai-catalog.ts at production · demosjarco/mat...

Magically All The Things AI. Contribute to demosjarco/matt-ai development by creating an account on GitHub.

VVictor API call to the cf: https://developers.cloudflare.com/api/operations/workers-ai-...

V

Victor•6/28/24, 7:32 PM

@Perry Sahnow because these count towards the global rate limit (1200/5m - https://developers.cloudflare.com/fundamentals/api/reference/limits/), you could cache the api results or go the build step method

PPerry Sahnow Yeah they presumably don't change more often than daily

V

Victor•6/28/24, 7:40 PM

I personally have mine set to update weekly and just watch and see how big of a commit (if any) happens in a given week - adjust from there. I did ask michelle about scheduled update cycle of models going forward, but they don't have any planned yet

云

云•6/28/24, 11:42 PM

huh i think the ai isn't recognizing my tools?

云

云•6/28/24, 11:43 PM

云

云•6/28/24, 11:43 PM

export const factorization = tool({
    description: 'Prime factorize any number even if they are very large',
    parameters: {
        type: 'object',
        properties: {
            number: {
                type: 'string',
                description: 'the number to factorize'
            }
        },
        required: ['number']
    },
    name: 'factorize-num',

    async function({ number }) {
        console.log('huh', number);
        return await factorize(number);
    }
});

export const factorization = tool({
    description: 'Prime factorize any number even if they are very large',
    parameters: {
        type: 'object',
        properties: {
            number: {
                type: 'string',
                description: 'the number to factorize'
            }
        },
        required: ['number']
    },
    name: 'factorize-num',

    async function({ number }) {
        console.log('huh', number);
        return await factorize(number);
    }
});

export const factorization = tool({
    description: 'Prime factorize any number even if they are very large',
    parameters: {
        type: 'object',
        properties: {
            number: {
                type: 'string',
                description: 'the number to factorize'
            }
        },
        required: ['number']
    },
    name: 'factorize-num',

    async function({ number }) {
        console.log('huh', number);
        return await factorize(number);
    }
});

export const factorization = tool({
    description: 'Prime factorize any number even if they are very large',
    parameters: {
        type: 'object',
        properties: {
            number: {
                type: 'string',
                description: 'the number to factorize'
            }
        },
        required: ['number']
    },
    name: 'factorize-num',

    async function({ number }) {
        console.log('huh', number);
        return await factorize(number);
    }
});

云

云•6/28/24, 11:43 PM

the function is not being called at all

云

云•6/28/24, 11:43 PM

{
    "response": "The number you've provided, 1203210203982198283, is a large number and appears to be an integer. However, finding the prime factorization of such a large number is not practical to do by hand, as it typically involves the use of specialized algorithms and computational resources. \n\nIn general, the factorization of large numbers is often done using numerical methods or mathematical software, such as the quadratic sieve, trial division, or Lenstra elliptic curve factorization, methods typically employed in cryptography or number theory research.\n\nFor all practical purposes, we would use computational tools to find the prime factorization of this number. To get an approximate factorization, you might use an online calculator or a programming language like Python with a library that supports number theory, such as `sympy`:\n\n\`\`\`python\nimport sympy as sp\n\nnumber = 1203210203982198283\n_factors = sp.factorint(number)\n_factors\n\`\`\`\nYou would need to run this code in an environment where you have the `sympy` library installed.\n\nIf you just want to know if it's a prime number, you should also consider that finding the factorization of a very large number to determine primality is computationally expensive, and for such a large number, it's highly unlikely to be a prime.\n\nIf you're seeking a prime factorization for educational purposes or a specific reason, please provide more context, and I can try to help further. Otherwise, it's best to use specialized software or an online tool to get the factorization."
}

{
    "response": "The number you've provided, 1203210203982198283, is a large number and appears to be an integer. However, finding the prime factorization of such a large number is not practical to do by hand, as it typically involves the use of specialized algorithms and computational resources. \n\nIn general, the factorization of large numbers is often done using numerical methods or mathematical software, such as the quadratic sieve, trial division, or Lenstra elliptic curve factorization, methods typically employed in cryptography or number theory research.\n\nFor all practical purposes, we would use computational tools to find the prime factorization of this number. To get an approximate factorization, you might use an online calculator or a programming language like Python with a library that supports number theory, such as `sympy`:\n\n\`\`\`python\nimport sympy as sp\n\nnumber = 1203210203982198283\n_factors = sp.factorint(number)\n_factors\n\`\`\`\nYou would need to run this code in an environment where you have the `sympy` library installed.\n\nIf you just want to know if it's a prime number, you should also consider that finding the factorization of a very large number to determine primality is computationally expensive, and for such a large number, it's highly unlikely to be a prime.\n\nIf you're seeking a prime factorization for educational purposes or a specific reason, please provide more context, and I can try to help further. Otherwise, it's best to use specialized software or an online tool to get the factorization."
}

{
    "response": "The number you've provided, 1203210203982198283, is a large number and appears to be an integer. However, finding the prime factorization of such a large number is not practical to do by hand, as it typically involves the use of specialized algorithms and computational resources. \n\nIn general, the factorization of large numbers is often done using numerical methods or mathematical software, such as the quadratic sieve, trial division, or Lenstra elliptic curve factorization, methods typically employed in cryptography or number theory research.\n\nFor all practical purposes, we would use computational tools to find the prime factorization of this number. To get an approximate factorization, you might use an online calculator or a programming language like Python with a library that supports number theory, such as `sympy`:\n\n\`\`\`python\nimport sympy as sp\n\nnumber = 1203210203982198283\n_factors = sp.factorint(number)\n_factors\n\`\`\`\nYou would need to run this code in an environment where you have the `sympy` library installed.\n\nIf you just want to know if it's a prime number, you should also consider that finding the factorization of a very large number to determine primality is computationally expensive, and for such a large number, it's highly unlikely to be a prime.\n\nIf you're seeking a prime factorization for educational purposes or a specific reason, please provide more context, and I can try to help further. Otherwise, it's best to use specialized software or an online tool to get the factorization."
}

{
    "response": "The number you've provided, 1203210203982198283, is a large number and appears to be an integer. However, finding the prime factorization of such a large number is not practical to do by hand, as it typically involves the use of specialized algorithms and computational resources. \n\nIn general, the factorization of large numbers is often done using numerical methods or mathematical software, such as the quadratic sieve, trial division, or Lenstra elliptic curve factorization, methods typically employed in cryptography or number theory research.\n\nFor all practical purposes, we would use computational tools to find the prime factorization of this number. To get an approximate factorization, you might use an online calculator or a programming language like Python with a library that supports number theory, such as `sympy`:\n\n\`\`\`python\nimport sympy as sp\n\nnumber = 1203210203982198283\n_factors = sp.factorint(number)\n_factors\n\`\`\`\nYou would need to run this code in an environment where you have the `sympy` library installed.\n\nIf you just want to know if it's a prime number, you should also consider that finding the factorization of a very large number to determine primality is computationally expensive, and for such a large number, it's highly unlikely to be a prime.\n\nIf you're seeking a prime factorization for educational purposes or a specific reason, please provide more context, and I can try to help further. Otherwise, it's best to use specialized software or an online tool to get the factorization."
}

云

云•6/28/24, 11:45 PM

didn't work even if i change the type of number to "number"

云

云•6/28/24, 11:51 PM

nvm i got it fixed

DDhravya Shah Hi everyone! we just made making AI agents 10x easier with a new open source pac...

M

MissS•6/30/24, 3:50 AM

Can this be done from durable objects?

S

scotto•6/30/24, 5:27 PM

News for multilingual embedding model ?

C

csilk•7/1/24, 4:41 AM

qq; is there a limit on the response length from the LLM?

C

csilk•7/1/24, 6:23 AM

And, a "less quick" question
Is there a way to do a

json_format

json_format

json_format

json_format response with workers AI? (like what OpenAI supports)
Specifically trying to get an LLM to take an input like "dogs" with a system message of "generate a trivia question based on the topic and respond in json format of

{ question: "string", answer: "string" }

{ question: "string", answer: "string" }

{ question: "string", answer: "string" }

{ question: "string", answer: "string" }
Do the worker ai response is

{question: "what is the best dog", answer: "all of them"}

{question: "what is the best dog", answer: "all of them"}

{question: "what is the best dog", answer: "all of them"}

{question: "what is the best dog", answer: "all of them"} (made this up

)

Ccsilk qq; is there a limit on the response length from the LLM?

R

rob•7/1/24, 10:48 AM

Ya each model has diff max token output

DDhravya Shah which ones do you wanna see? 👀

S

scotto•7/1/24, 12:23 PM

BAAI/bge-m3 is ok, from the same family of the already supported

A

AngusMa•7/1/24, 2:05 PM

Why didn’t Workers AI Playground work?

AAngusMa Why didn’t Workers AI Playground work?

P

Ping for toast•7/1/24, 4:00 PM

homepage demo is also broken

anyone know of an open source model better than whisper? If not anyone tried training it?

Similar Threads