Search
150 results for “jd7h”
-
We were looking for a local tokenizer for counting the number of input tokens before calling the gemini-embedding-001 endpoint on vertex AI. Turns out this Gemma tokenizer returns exactly the same number of tokens as the usage in the embeddings result `embedding.statistics.token_count` of the Gemini embeddings endpoint. Tested on 2000 datapoints. 😁
-
We were looking for a local tokenizer for counting the number of input tokens before calling the gemini-embedding-001 endpoint on vertex AI. Turns out this Gemma tokenizer returns exactly the same number of tokens as the usage in the embeddings result `embedding.statistics.token_count` of the Gemini embeddings endpoint. Tested on 2000 datapoints. 😁
-
Dear opensource developers, if you build ML libraries on top of other ML libraries, please expose the underlying APIs for:
- loading custom model weights
- saving model weights
- saving pipelines
- exporting safetensorsThis way, you support your users in working with local models, instead of making them extra dependent on external model hosting parties like Google and HuggingFace.
#ml #mlops #ai #generativeai #huggingface #transformers #diffusers #opensource
-
Cards Against Humanity has launched a Black Friday prank: social media site "Yowza". Too bad about the "referral link" spam posts on hashtag #FuckXJoinYowza, but I do love the brutalist design of the website. And the site "has no hate speech"...because "yowza" seems the only allowed text on the platform.
-
Dear opensource developers, if you build ML libraries on top of other ML libraries, please expose the underlying APIs for:
- loading custom model weights
- saving model weights
- saving pipelines
- exporting safetensorsThis way, you support your users in working with local models, instead of making them extra dependent on external model hosting parties like Google and HuggingFace.
#ml #mlops #ai #generativeai #huggingface #transformers #diffusers #opensource
-
Dear opensource developers, if you build ML libraries on top of other ML libraries, please expose the underlying APIs for:
- loading custom model weights
- saving model weights
- saving pipelines
- exporting safetensorsThis way, you support your users in working with local models, instead of making them extra dependent on external model hosting parties like Google and HuggingFace.
#ml #mlops #ai #generativeai #huggingface #transformers #diffusers #opensource
-
Dear opensource developers, if you build ML libraries on top of other ML libraries, please expose the underlying APIs for:
- loading custom model weights
- saving model weights
- saving pipelines
- exporting safetensorsThis way, you support your users in working with local models, instead of making them extra dependent on external model hosting parties like Google and HuggingFace.
#ml #mlops #ai #generativeai #huggingface #transformers #diffusers #opensource
-
Dear opensource developers, if you build ML libraries on top of other ML libraries, please expose the underlying APIs for:
- loading custom model weights
- saving model weights
- saving pipelines
- exporting safetensorsThis way, you support your users in working with local models, instead of making them extra dependent on external model hosting parties like Google and HuggingFace.
#ml #mlops #ai #generativeai #huggingface #transformers #diffusers #opensource
-
I am in Eindhoven today for AI Summit Brainport. I’ll be participating in the Startup track. Looking forward to seeing what cool things people are building with generative AI/LLMs. Come say hi if you’re there as well!
#eindhoven #brainport #aisummitbrainport #llms #generativeai #startups #events
-
"We've now created our first deep learning neural network from scratch. And we did it in Microsoft Excel, everyone's favorite artificial intelligence tool."
- Jeremy Howard in https://www.youtube.com/watch?v=hBBOjCiFcuo&t=3862s
-
"We've now created our first deep learning neural network from scratch. And we did it in Microsoft Excel, everyone's favorite artificial intelligence tool."
- Jeremy Howard in https://www.youtube.com/watch?v=hBBOjCiFcuo&t=3862s
-
"We've now created our first deep learning neural network from scratch. And we did it in Microsoft Excel, everyone's favorite artificial intelligence tool."
- Jeremy Howard in https://www.youtube.com/watch?v=hBBOjCiFcuo&t=3862s
-
"We've now created our first deep learning neural network from scratch. And we did it in Microsoft Excel, everyone's favorite artificial intelligence tool."
- Jeremy Howard in https://www.youtube.com/watch?v=hBBOjCiFcuo&t=3862s
-
New blogpost, this time about Dutch artist Niels van Spaendonck: https://www.judithvanstegeren.com/blog/niels-van-spaendonck-kunstenaar/
-
New blogpost, this time about Dutch artist Niels van Spaendonck: https://www.judithvanstegeren.com/blog/niels-van-spaendonck-kunstenaar/
-
New blogpost, this time about Dutch artist Niels van Spaendonck: https://www.judithvanstegeren.com/blog/niels-van-spaendonck-kunstenaar/
-
New blogpost, this time about Dutch artist Niels van Spaendonck: https://www.judithvanstegeren.com/blog/niels-van-spaendonck-kunstenaar/
-
Nieuwe recepten op Mosterdgeel:
- Chicken Katsu Curry: https://www.mosterdgeel.nl/recepten/katsu-curry/
- Boterbier (eigenlijk het verkeerde jaargetijde, maar he): https://www.mosterdgeel.nl/recepten/boterbier/
- Vegan bloemkoolstoof: https://www.mosterdgeel.nl/recepten/vegan-bloemkoolstoof-met-port-en-chocola/ -
Nieuwe recepten op Mosterdgeel:
- Chicken Katsu Curry: https://www.mosterdgeel.nl/recepten/katsu-curry/
- Boterbier (eigenlijk het verkeerde jaargetijde, maar he): https://www.mosterdgeel.nl/recepten/boterbier/
- Vegan bloemkoolstoof: https://www.mosterdgeel.nl/recepten/vegan-bloemkoolstoof-met-port-en-chocola/ -
Nieuwe recepten op Mosterdgeel:
- Chicken Katsu Curry: https://www.mosterdgeel.nl/recepten/katsu-curry/
- Boterbier (eigenlijk het verkeerde jaargetijde, maar he): https://www.mosterdgeel.nl/recepten/boterbier/
- Vegan bloemkoolstoof: https://www.mosterdgeel.nl/recepten/vegan-bloemkoolstoof-met-port-en-chocola/ -
Nieuwe recepten op Mosterdgeel:
- Chicken Katsu Curry: https://www.mosterdgeel.nl/recepten/katsu-curry/
- Boterbier (eigenlijk het verkeerde jaargetijde, maar he): https://www.mosterdgeel.nl/recepten/boterbier/
- Vegan bloemkoolstoof: https://www.mosterdgeel.nl/recepten/vegan-bloemkoolstoof-met-port-en-chocola/ -
Nieuw recept op Mosterdgeel.nl: https://www.mosterdgeel.nl/recepten/epische-restjesnasi/
-
Nieuw recept op Mosterdgeel.nl: https://www.mosterdgeel.nl/recepten/epische-restjesnasi/
-
Nieuw recept op Mosterdgeel.nl: https://www.mosterdgeel.nl/recepten/epische-restjesnasi/
-
Nieuw recept op Mosterdgeel.nl: https://www.mosterdgeel.nl/recepten/epische-restjesnasi/
-
Fitting an LLM on a GPU is a bit like photography. Model weights = film sensitivity, activation size = shutter speed, I/O tensors = aperture. These 3 dials control your model's memory footprint, just as they shape a photo's exposure.
Just realised this while trying to fit Llama 3.1 on my 24GB GPU with TRT-LLM: https://nvidia.github.io/TensorRT-LLM/reference/memory.html.