Mariusz Kurman
@mkurman.bsky.social
AI Tech Lead @ Kruk SA | CEO @ MedIT Solutions | MD | Medcases.io app creator
It has a minor bug that requires further fine-tuning (sometimes it starts with the <|python_tag|> instead of <Thought>.
January 4, 2025 at 1:17 PM
It has a minor bug that requires further fine-tuning (sometimes it starts with the <|python_tag|> instead of <Thought>.
I will definitely give it a try!
December 4, 2024 at 10:28 PM
I will definitely give it a try!
PS. You can find the model mentioned here: huggingface.co/meditsolutio...
License: Apache 2.0 4/4
License: Apache 2.0 4/4
meditsolutions/SmolLM2-MedIT-Upscale-2B · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
December 2, 2024 at 2:54 PM
PS. You can find the model mentioned here: huggingface.co/meditsolutio...
License: Apache 2.0 4/4
License: Apache 2.0 4/4
the model achieved better results in IFEval and a higher overall average score in Open LLM Leaderboard
I consider this a big success 😇, since surpassing the original in metrics is often very time-consuming, generates high costs, and doesn't always work out. 3/4
I consider this a big success 😇, since surpassing the original in metrics is often very time-consuming, generates high costs, and doesn't always work out. 3/4
meditsolutions/SmolLM2-MedIT-Upscale-2B · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
December 2, 2024 at 2:54 PM
the model achieved better results in IFEval and a higher overall average score in Open LLM Leaderboard
I consider this a big success 😇, since surpassing the original in metrics is often very time-consuming, generates high costs, and doesn't always work out. 3/4
I consider this a big success 😇, since surpassing the original in metrics is often very time-consuming, generates high costs, and doesn't always work out. 3/4
In total, not much really, since we don't have the original trained under the same conditions as our upscale. However...
1. We scaled up the model without losing its quality
2. We confirmed that the method we devised works
3. After extremely short fine-tuning, 2/4
1. We scaled up the model without losing its quality
2. We confirmed that the method we devised works
3. After extremely short fine-tuning, 2/4
meditsolutions/SmolLM2-MedIT-Upscale-2B · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
December 2, 2024 at 2:54 PM
In total, not much really, since we don't have the original trained under the same conditions as our upscale. However...
1. We scaled up the model without losing its quality
2. We confirmed that the method we devised works
3. After extremely short fine-tuning, 2/4
1. We scaled up the model without losing its quality
2. We confirmed that the method we devised works
3. After extremely short fine-tuning, 2/4