Danh Tran
danhtran2mind
AI & ML interests
๐๐ค AI Engineer. Building the future of intelligence. ๐ง ๐ก
Organizations
This collection includes text to audio and text to music
-
danhtran2mind/viet-news-sum-mt5-small-finetune
Summarization โข 0.3B โข Updated โข 12 -
danhtran2mind/En2Vi-Translation-Transformer-TensorFlow
Translation โข Updated โข 17 โข 1 -
danhtran2mind/vi-nutrition-gpt2-finetune
Text Generation โข 0.1B โข Updated โข 1 -
danhtran2mind/vi-medical-mt5-finetune-qa
Question Answering โข 0.3B โข Updated
This is Mini LLMs Model, which has number of parameters lesser and or 1B
-
litert-community/Gemma3-1B-IT
Text Generation โข Updated โข 26.2k โข 554 -
meta-llama/Llama-3.2-1B
Text Generation โข 1B โข Updated โข 1.9M โข 2.33k -
meta-llama/Llama-3.2-1B-Instruct
Text Generation โข 1B โข Updated โข 4.15M โข โข 1.32k -
meta-llama/Llama-Guard-3-1B-INT4
Text Generation โข Updated โข 50 โข 27
-
Stable Diffusion 3.5 Large
๐2kGenerate images with SD3.5
-
Kolors Character With Flux
๐คน903Kolors Character to keep character developed with Flux
-
X Portrait
๐คช222Expressive Portrait Animation w/ Hierarchical Motion Attentยฐ
-
InfiniteYou-FLUX
๐ธ1.1kFlexible Photo Recrafting While Preserving Your Identity
-
danhtran2mind/controlnet-sd-2-1
Updated -
danhtran2mind/Ghibli-Stable-Diffusion-2.1-Base-finetuning-INT8
Text-to-Image โข Updated -
danhtran2mind/Ghibli-Stable-Diffusion-2.1-Base-finetuning-INT4
Text-to-Image โข Updated -
danhtran2mind/Ghibli-Stable-Diffusion-2.1-Base-finetuning-FP8
Text-to-Image โข Updated
DanhTran2Mind's fine-tuned LLMs use LoRA for efficiency or full fine-tuning for top performance, customized to each model hub and task.
This collection includes text to audio and text to music
-
danhtran2mind/viet-news-sum-mt5-small-finetune
Summarization โข 0.3B โข Updated โข 12 -
danhtran2mind/En2Vi-Translation-Transformer-TensorFlow
Translation โข Updated โข 17 โข 1 -
danhtran2mind/vi-nutrition-gpt2-finetune
Text Generation โข 0.1B โข Updated โข 1 -
danhtran2mind/vi-medical-mt5-finetune-qa
Question Answering โข 0.3B โข Updated
-
danhtran2mind/controlnet-sd-2-1
Updated -
danhtran2mind/Ghibli-Stable-Diffusion-2.1-Base-finetuning-INT8
Text-to-Image โข Updated -
danhtran2mind/Ghibli-Stable-Diffusion-2.1-Base-finetuning-INT4
Text-to-Image โข Updated -
danhtran2mind/Ghibli-Stable-Diffusion-2.1-Base-finetuning-FP8
Text-to-Image โข Updated
DanhTran2Mind's fine-tuned LLMs use LoRA for efficiency or full fine-tuning for top performance, customized to each model hub and task.
This is Mini LLMs Model, which has number of parameters lesser and or 1B
-
litert-community/Gemma3-1B-IT
Text Generation โข Updated โข 26.2k โข 554 -
meta-llama/Llama-3.2-1B
Text Generation โข 1B โข Updated โข 1.9M โข 2.33k -
meta-llama/Llama-3.2-1B-Instruct
Text Generation โข 1B โข Updated โข 4.15M โข โข 1.32k -
meta-llama/Llama-Guard-3-1B-INT4
Text Generation โข Updated โข 50 โข 27
-
Stable Diffusion 3.5 Large
๐2kGenerate images with SD3.5
-
Kolors Character With Flux
๐คน903Kolors Character to keep character developed with Flux
-
X Portrait
๐คช222Expressive Portrait Animation w/ Hierarchical Motion Attentยฐ
-
InfiniteYou-FLUX
๐ธ1.1kFlexible Photo Recrafting While Preserving Your Identity